1558 public code units, none of them silent. This is the whole
public surface of the library, measured on 2026-09-11 and regenerated by
scripts/capability_status.py. Nothing here is typed by hand.
Checked is not a correctness certificate for the number a function returns. It means the fabrication class was examined: on input where nothing is measurable, the unit refuses instead of handing back a neutral-looking value. The reason column states what each row does and does not establish.
The same rows as a machine-readable feed:
capability-status.json.
One object per code unit, carrying its state, the reason, the evidence it rests on
and the tests that pin it, so a claim on this page can be checked rather than
taken.
| Area | Checked | Fix pending | Not checked | Total |
|---|---|---|---|---|
| Fairness metrics | 152 | 0 | 92 | 244 |
| Post-processing mitigation | 126 | 11 | 52 | 189 |
| In-processing mitigation | 112 | 17 | 46 | 175 |
| LLM fairness testing | 81 | 4 | 60 | 145 |
| Operations (other) | 57 | 2 | 71 | 130 |
| Preprocessing mitigation | 51 | 15 | 35 | 101 |
| Explainability (XAI) | 36 | 0 | 45 | 81 |
| CI/CD gates | 34 | 1 | 42 | 77 |
| Reporting | 37 | 3 | 37 | 77 |
| Monitoring | 53 | 9 | 3 | 65 |
| Bias detection | 37 | 0 | 28 | 65 |
| Agent fairness testing | 29 | 0 | 32 | 61 |
| Report rendering | 1 | 0 | 56 | 57 |
| Top level | 9 | 0 | 30 | 39 |
| MCP tools | 7 | 5 | 11 | 23 |
| Validity axis | 4 | 0 | 7 | 11 |
| Networking | 3 | 0 | 6 | 9 |
| Vision | 4 | 0 | 2 | 6 |
| Legal | 0 | 0 | 3 | 3 |
| Code unit | Status | Area | Kind | What is established |
|---|---|---|---|---|
vfairness._names.name_token_list | Not checked | Top level | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness._names.name_tokens | Not checked | Top level | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness._names.resolve_attribute_key | Checked | Top level | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness._names.tokens_contain | Not checked | Top level | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness._not_assessed.warn_not_assessed | Checked | Top level | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness._triage.is_flag | Not checked | Top level | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness._triage.is_measured | Not checked | Top level | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness._triage.measured_values | Not checked | Top level | function | executed, and on 2 world(s) where nothing was measurable (all_nan_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness._triage.unmeasurable_reason | Not checked | Top level | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.agents.action_bias.ActionBiasAnalyzer | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.agents.action_bias.ActionBiasAnalyzer.analyze_delegation | Not checked | Agent fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.agents.action_bias.ActionBiasAnalyzer.analyze_outcomes | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.agents.action_bias.ActionBiasResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.agents.correspondence.CorrespondenceResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.agents.correspondence.CorrespondenceTester | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.agents.correspondence.CorrespondenceTester.analyze_outcomes | Not checked | Agent fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.agents.correspondence.CorrespondenceTester.create_paired_artifacts | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.agents.correspondence.CorrespondenceTester.four_fifths_rule | Not checked | Agent fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.agents.pipeline_tracker.PipelineTracker | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.agents.pipeline_tracker.PipelineTracker.compute_cumulative | Not checked | Agent fairness testing | method | executed, and on 7 world(s) where nothing was measurable (all_nan_scores, constant_scores, n_equals_2) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.agents.pipeline_tracker.PipelineTracker.identify_bias_source | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.agents.pipeline_tracker.PipelineTracker.record_stage | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.agents.pipeline_tracker.StageResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.agents.rag_bias.RAGBiasAnalyzer | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.agents.rag_bias.RAGBiasAnalyzer.analyze_output | Not checked | Agent fairness testing | method | executed, and on 6 world(s) where nothing was measurable (constant_scores, n_equals_2, one_label_only) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.agents.rag_bias.RAGBiasAnalyzer.analyze_retrieval | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.agents.rag_bias.RAGBiasAnalyzer.full_analysis | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.agents.rag_bias.RAGBiasResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.agents.temporal.TemporalTracker | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.agents.temporal.TemporalTracker.compute_trajectory | Not checked | Agent fairness testing | method | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.agents.temporal.TemporalTracker.detect_drift | Checked | Agent fairness testing | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.agents.temporal.TemporalTracker.detect_drift_cusum | Not checked | Agent fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.agents.temporal.TemporalTracker.detect_drift_ewma | Not checked | Agent fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.agents.temporal.TemporalTracker.detect_feedback_loop | Not checked | Agent fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.agents.temporal.TemporalTracker.record_turn | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.agents.temporal.TrajectoryResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.agents.tool_bias.ToolBiasAuditor | Checked | Agent fairness testing | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.agents.tool_bias.ToolBiasAuditor.analyze_tool_calls | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.agents.tool_bias.ToolBiasAuditor.compute_selection_disparity | Not checked | Agent fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.agents.tool_bias.ToolBiasResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.branding.branding_enabled | Not checked | Top level | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.branding.set_branding | Checked | Top level | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.create_calibration_dashboard | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.create_fairness_dashboard | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.compute_group_rate | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.compute_group_statistic | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_group | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_group_proportions | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_group_sizes | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_indices | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_info | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_invalid_groups | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_mask | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_size | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.get_valid_groups | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.GroupManager.iter_groups | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._grouping.compute_max_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._metric_direction.MetricDirection | Not checked | Fairness metrics | class | could not be constructed without a hand-built fixture |
vfairness.evaluation.vfairness_metrics._metric_direction.ThresholdOutcome | Not checked | Fairness metrics | class | could not be constructed without a hand-built fixture |
vfairness.evaluation.vfairness_metrics._metric_direction.check_threshold | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics._metric_direction.improvement_amount | Not checked | Fairness metrics | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.evaluation.vfairness_metrics._metric_direction.is_ratio_metric | Not checked | Fairness metrics | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.evaluation.vfairness_metrics._metric_direction.metric_direction | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics._metric_direction.relax_threshold | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics._statistics.IntervalType | Not checked | Fairness metrics | class | could not be constructed without a hand-built fixture |
vfairness.evaluation.vfairness_metrics._statistics.MultipleTestingResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics._statistics.MultipleTestingResult.to_dict | Checked | Fairness metrics | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics._statistics.StatisticalResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics._statistics.StatisticalResult.to_dict | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.apply_multiple_testing_correction | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.bayesian_difference_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.bayesian_mean_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.bayesian_proportion_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.benjamini_hochberg_correction | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.bonferroni_correction | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.bootstrap_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.bootstrap_over_index | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.cohens_d | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.cohens_h | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.cohens_h_interpretation | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.compute_metric_with_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.detectability | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.empirical_likelihood_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.fisher_exact_test | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.group_reliability | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.interpret_effect_size | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.min_attainable_p_fisher | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.min_attainable_p_mcnemar | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.min_attainable_p_permutation | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.min_attainable_p_sign_flip | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.minimum_detectable_effect | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.odds_ratio | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.power_warning | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.proportion_z_test | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.reliability_tier | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics._statistics.risk_ratio | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.select_method | Checked | Fairness metrics | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics._statistics.sequential_fairness_test | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.simultaneous_disparity_bounds | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.stratified_bootstrap_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._statistics.validate_confidence_level | Checked | Fairness metrics | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics._statistics.wilson_score_interval | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics._validation.check_consistent_length | Not checked | Fairness metrics | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.evaluation.vfairness_metrics._validation.coerce_to_array | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics._validation.reject_swapped_labels_and_scores | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics._validation.validate_binary_labels | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics._validation.validate_inputs | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics._validation.validate_probabilities | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer | Checked | Fairness metrics | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.clear_cache | Checked | Fairness metrics | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.compare_with_aequitas | Checked | Fairness metrics | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.compare_with_fairlearn | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.compute_all_metrics | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.demographic_parity_difference | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.disable_fair_explainer | Checked | Fairness metrics | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.enable_fair_explainer | Checked | Fairness metrics | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.equal_opportunity_difference | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.equalized_odds_difference | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.explain_metric | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.get_explanations | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.get_report | Not checked | Fairness metrics | method | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.mae_parity_difference | Checked | Fairness metrics | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.analyzer.FairnessAnalyzer.report_to_svg | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.analyzer.MetricResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.analyzer.MetricResult.to_dict | Not checked | Fairness metrics | method | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.attribution.AttributionResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.attribution.AttributionResult.to_dict | Not checked | Fairness metrics | method | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.attribution.AttributionResult.top | Not checked | Fairness metrics | method | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.attribution.FeatureAttributionExplainer | Checked | Fairness metrics | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.attribution.FeatureAttributionExplainer.explain_decision | Not checked | Fairness metrics | method | could not be called without a hand-built fixture |
vfairness.evaluation.vfairness_metrics.attribution.FeatureAttributionExplainer.global_importance | Not checked | Fairness metrics | method | could not be called without a hand-built fixture |
vfairness.evaluation.vfairness_metrics.attribution.FeatureAttributionExplainer.shapley_matrix | Not checked | Fairness metrics | method | could not be called without a hand-built fixture |
vfairness.evaluation.vfairness_metrics.attribution.FeatureContribution | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.attribution.FeatureContribution.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.classification.accuracy_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.auroc_parity | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.calibration_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.compute_effect_sizes | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.classification.conditional_adverse_impact | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.conditional_demographic_disparity | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.conditional_demographic_disparity_with_ci | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.classification.demographic_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.demographic_parity_difference_with_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.demographic_parity_ratio | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.disparate_impact_ratio | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.disparate_impact_ratio_with_ci | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.equal_opportunity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.equal_opportunity_difference_with_ci | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.classification.equalized_odds_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.equalized_odds_difference_with_ci | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.classification.fnr_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.fpr_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.fpr_parity_difference_with_ci | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.classification.get_group_metrics | Not checked | Fairness metrics | function | executed, and on 2 world(s) where nothing was measurable (all_nan_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.evaluation.vfairness_metrics.classification.get_group_metrics_with_ci | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.classification.negative_predictive_value_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.negative_predictive_value_difference_with_ci | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.classification.net_benefit_parity | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.predictive_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.classification.predictive_parity_difference_with_ci | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.classification.selection_rate_disparity_matrix | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.classification.worst_group_accuracy | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.counterfactual_metric.CounterfactualFairnessResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.counterfactual_metric.CounterfactualFairnessResult.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.counterfactual_metric.counterfactual_fairness | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.create_fairness_dashboard | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.discovery.ColumnRole | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.discovery.ColumnRole.to_dict | Not checked | Fairness metrics | method | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.discovery.FairnessViolation | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.discovery.FairnessViolation.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.discovery.ProtectedAttributeCandidate | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.discovery.ProtectedAttributeCandidate.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.discovery.ProxyScanIncompleteWarning | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.discovery.association_strength | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.discovery.classify_column_roles | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.discovery.detect_protected_attributes | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.discovery.discover_intersectional_groups | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.discovery.identify_proxy_features | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.discovery.rank_fairness_issues | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.discovery.scan_fairness_violations | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.explainer.FairExplAIner | Checked | Fairness metrics | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.explainer.FairExplAIner.explain_confidence_interval | Not checked | Fairness metrics | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.evaluation.vfairness_metrics.explainer.FairExplAIner.explain_effect_size | Not checked | Fairness metrics | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.evaluation.vfairness_metrics.explainer.FairExplAIner.explain_metric | Not checked | Fairness metrics | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.evaluation.vfairness_metrics.explainer.FairExplAIner.explain_report | Not checked | Fairness metrics | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.evaluation.vfairness_metrics.explainer.MetricExplanation | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.explainer.MetricExplanation.to_dict | Not checked | Fairness metrics | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.evaluation.vfairness_metrics.explainer.explain_fairness_report | Not checked | Fairness metrics | function | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.evaluation.vfairness_metrics.explainer.print_explanations | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.explanation_diagnostics.AdversarialProbeResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.explanation_diagnostics.attribution_stability | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.explanation_diagnostics.diagnose_local_attribution | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.explanation_diagnostics.multi_seed_adversarial_probe | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.explanation_diagnostics.removal_curve_auc | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.fairness_decomposition.FairnessDecompositionResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.fairness_decomposition.FairnessDecompositionResult.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.fairness_decomposition.fairness_decomposition | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.get_available_styles | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.get_palettes | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.integrations.FairnessAssertionError | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.integrations.assert_fairness | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.integrations.auto_log_fairness | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.integrations.create_fairness_callback | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.integrations.log_fairness_to_mlflow | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.integrations.log_fairness_to_wandb | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.intersectional.GroupAdvantage | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.intersectional.GroupAdvantage.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.intersectional.generate_structured_findings | Not checked | Fairness metrics | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.evaluation.vfairness_metrics.intersectional.get_group_rankings | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.intersectional.identify_privileged_groups | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.intersectional.intersectional_disparity_analysis | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.plot_confidence_intervals | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.plot_effect_sizes | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.plot_fairness_metrics | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.plot_fairness_report | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.plot_group_comparison | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.plot_group_disparity_heatmap | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.plot_metrics_radar | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.preview_palette | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.ranking.RankingFairnessResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.ranking.RankingFairnessResult.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.ranking.attention_weighted_rank_fairness | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.ranking.exposure_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.ranking.exposure_parity_ratio | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.ranking.get_ranking_group_metrics | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.ranking.normalized_discounted_kl_divergence | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.recourse.FeatureChange | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.recourse.FeatureChange.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.recourse.Recourse | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.recourse.Recourse.to_dict | Not checked | Fairness metrics | method | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.recourse.RecourseResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.recourse.RecourseResult.to_dict | Not checked | Fairness metrics | method | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.recourse.generate_recourse | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.regression.compute_regression_effect_sizes | Not checked | Fairness metrics | function | executed, and on 3 world(s) where nothing was measurable (all_nan_scores, empty, single_group) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.evaluation.vfairness_metrics.regression.get_group_metrics | Not checked | Fairness metrics | function | executed, and on 2 world(s) where nothing was measurable (all_nan_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.evaluation.vfairness_metrics.regression.mae_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.regression.mae_parity_difference_with_ci | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.regression.mean_prediction_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.regression.mean_prediction_difference_with_ci | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.regression.pricing_disparity | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.regression.pricing_disparity_with_ci | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.regression.r2_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.regression.residual_bias | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.regression.rmse_parity_difference | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.regression.rmse_parity_difference_with_ci | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.report.classification_fairness_report | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.report.print_report | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.report.regression_fairness_report | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.report_types.AssessmentReport | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.report_types.DataInfo | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.report_types.ExplanationsReport | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.report_types.FairnessReport | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.report_types.InsufficientEvidenceGroup | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.report_types.MetricStatusEntry | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.robustness.ContingencyTestResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.robustness.ContingencyTestResult.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.robustness.PermutationTestResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.robustness.PermutationTestResult.to_dict | Not checked | Fairness metrics | method | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.robustness.RobustMetricsResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.robustness.RobustMetricsResult.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.robustness.SensitivityResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.robustness.SensitivityResult.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.robustness.SubgroupAuditResult | Checked | Fairness metrics | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.evaluation.vfairness_metrics.robustness.SubgroupAuditResult.to_dict | Not checked | Fairness metrics | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.robustness.comprehensive_fairness_test | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.robustness.compute_robust_metrics | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.robustness.contingency_test | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.robustness.permutation_test | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.robustness.permutation_test_demographic_parity | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.robustness.permutation_test_equal_opportunity | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.robustness.robust_fairness_comparison | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.robustness.sensitivity_analysis | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.robustness.stress_test_fairness | Checked | Fairness metrics | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.evaluation.vfairness_metrics.robustness.subgroup_robustness_audit | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.robustness.test_equalized_odds_chi_square | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.save_fairness_plots | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.visualization.create_fairness_dashboard | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.visualization.get_available_styles | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.visualization.plot_confidence_intervals | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.visualization.plot_effect_sizes | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.visualization.plot_fairness_metrics | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.visualization.plot_fairness_report | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.visualization.plot_group_comparison | Checked | Fairness metrics | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.evaluation.vfairness_metrics.visualization.plot_group_disparity_heatmap | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.visualization.plot_metrics_radar | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.evaluation.vfairness_metrics.visualization.preview_palette | Not checked | Fairness metrics | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.evaluation.vfairness_metrics.visualization.save_fairness_plots | Not checked | Fairness metrics | function | called, but the call itself failed, so nothing was learned about it |
vfairness.exceptions.ConfigurationError | Checked | Top level | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.exceptions.InsufficientDataError | Checked | Top level | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.exceptions.InvalidDataError | Checked | Top level | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.exceptions.ProtectedAttributeError | Checked | Top level | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.exceptions.VfairnessError | Checked | Top level | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.explainer.ExplanationReport | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.explainer.ExplanationReport.to_dict | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.explainer.FairnessExplainer | Checked | Explainability (XAI) | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.get_available_styles | Not checked | Top level | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.get_palettes | Not checked | Top level | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.in_processing.analyzer.FairnessTrainingAnalyzer | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.analyzer.FairnessTrainingAnalyzer.analyze_tradeoffs | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.analyzer.FairnessTrainingAnalyzer.compare_methods | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.analyzer.FairnessTrainingAnalyzer.evaluate_baseline | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.analyzer.FairnessTrainingAnalyzer.full_analysis | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.analyzer.FairnessTrainingAnalyzer.generate_recommendation | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.analyzer.FairnessTrainingAnalyzer.get_data_summary | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.analyzer.FairnessTrainingAnalyzer.get_explanation | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.analyzer.FairnessTrainingReport | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.analyzer.FairnessTrainingReport.summary | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.analyzer.FairnessTrainingReport.to_dict | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.analyzer.FairnessTrainingReport.to_json | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.analyzer.FairnessTrainingReport.to_svg | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.analyzer.MethodComparison | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.analyzer.MethodComparison.to_dict | Not checked | In-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.in_processing.analyzer.TrainingRecommendation | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.analyzer.TrainingRecommendation.to_dict | Not checked | In-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.in_processing.analyzer.baseline_comparison_summary | Not checked | In-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.calibrators.group_calibrators.BetaCalibrator | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.calibrators.group_calibrators.BetaCalibrator.forward | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.BetaCalibrator.get_parameters | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.CalibrationAwareTrainer | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.CalibrationAwareTrainer.fine_tune_calibration | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.calibrators.group_calibrators.CalibrationAwareTrainer.train_step | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.calibrators.group_calibrators.CalibrationMethodType | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.calibrators.group_calibrators.CalibrationState | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.CalibrationState.to_dict | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.calibrators.group_calibrators.FocalCalibrator | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.calibrators.group_calibrators.FocalCalibrator.forward | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.calibrators.group_calibrators.FocalCalibrator.get_parameters | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.PlattScalingCalibrator | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.calibrators.group_calibrators.PlattScalingCalibrator.forward | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.PlattScalingCalibrator.get_parameters | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.TemperatureScalingCalibrator | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.calibrators.group_calibrators.TemperatureScalingCalibrator.forward | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.TemperatureScalingCalibrator.get_parameters | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.TrainableGroupCalibrator | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.calibrators.group_calibrators.TrainableGroupCalibrator.calibration_loss | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.calibrators.group_calibrators.TrainableGroupCalibrator.forward | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.TrainableGroupCalibrator.freeze | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.TrainableGroupCalibrator.get_calibration_state | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.calibrators.group_calibrators.TrainableGroupCalibrator.unfreeze | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.check_torch_available | Checked | In-processing mitigation | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.calibrators.group_calibrators.create_group_calibrator | Checked | In-processing mitigation | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.base.BaseFairnessConstraint | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.constraints.base.BaseFairnessConstraint.compute_violation | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.base.BaseFairnessConstraint.is_satisfied | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.BaseFairnessConstraint.signed_constraint_value | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.base.BoundedGroupLossConstraint | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.BoundedGroupLossConstraint.compute_violation | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.constraints.base.BoundedGroupLossConstraint.signed_constraint_value | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.constraints.base.ConstraintViolation | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.base.ConstraintViolation.to_dict | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.base.DemographicParityConstraint | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.DemographicParityConstraint.compute_violation | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.constraints.base.DemographicParityConstraint.signed_constraint_value | Checked | In-processing mitigation | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.constraints.base.EqualOpportunityConstraint | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.EqualOpportunityConstraint.compute_violation | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.EqualOpportunityConstraint.signed_constraint_value | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.EqualizedOddsConstraint | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.EqualizedOddsConstraint.compute_violation | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.EqualizedOddsConstraint.signed_constraint_value | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.FairnessConstraintType | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.constraints.base.FalsePositiveRateParityConstraint | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.FalsePositiveRateParityConstraint.compute_violation | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.FalsePositiveRateParityConstraint.signed_constraint_value | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.OptimizationResult | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.base.OptimizationResult.to_dict | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.base.create_constraint | Checked | In-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.EnsembleClassifier | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.reductions.EnsembleClassifier.predict | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.constraints.reductions.EnsembleClassifier.predict_proba | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.constraints.reductions.ExponentiatedGradient | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.ExponentiatedGradient.fit | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.constraints.reductions.ExponentiatedGradient.get_result | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.reductions.ExponentiatedGradient.predict | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.constraints.reductions.ExponentiatedGradient.predict_proba | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.constraints.reductions.GridSearch | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.GridSearch.fit | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.GridSearch.predict | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.LagrangianState | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.reductions.ReductionResult | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.reductions.ReductionResult.predict | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.ReductionResult.predict_proba | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.ReductionResult.to_dict | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.ThresholdOptimizer | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.constraints.reductions.ThresholdOptimizer.fit | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.constraints.reductions.ThresholdOptimizer.get_thresholds | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.constraints.reductions.ThresholdOptimizer.predict | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.diagnostics.adversarial_convergence_diagnostics | Not checked | In-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.diagnostics.sklearn_adversarial_debiasing | Not checked | In-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.loss_functions.adversarial.AdversarialDebiasingLoss | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.loss_functions.adversarial.AdversarialDebiasingLoss.get_adversary_accuracy | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.loss_functions.adversarial.AdversarialDebiasingLoss.to | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.AdversarialDebiasingLoss.update_adversary | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.loss_functions.adversarial.Adversary | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.loss_functions.adversarial.Adversary.forward | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.FairRepresentationLoss | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.loss_functions.adversarial.FairRepresentationLoss.forward | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.loss_functions.adversarial.FairRepresentationLoss.to | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.GradientReversalFunction | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.GradientReversalFunction.backward | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.GradientReversalFunction.forward | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.GradientReversalLayer | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.GradientReversalLayer.forward | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.GradientReversalLayer.set_lambda | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.ProjectedAdversarialLoss | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.loss_functions.adversarial.ProjectedAdversarialLoss.to | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.adversarial.ProjectedAdversarialLoss.update_adversary | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.loss_functions.base.BaseFairnessLoss | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.loss_functions.base.BaseFairnessLoss.end_epoch | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.loss_functions.base.BaseFairnessLoss.forward | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.loss_functions.base.BaseFairnessLoss.get_training_history | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.loss_functions.base.BaseFairnessLoss.reset_history | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.loss_functions.base.BaseFairnessLoss.set_epoch | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.loss_functions.base.BaseLossType | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.loss_functions.base.FairnessMetricType | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.loss_functions.base.LossComponents | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.base.LossComponents.to_dict | Not checked | In-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.in_processing.loss_functions.base.TrainingMetrics | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.loss_functions.base.TrainingMetrics.to_dict | Not checked | In-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.in_processing.loss_functions.base.check_torch_available | Checked | In-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.loss_functions.base.compute_group_rates | Not checked | In-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.loss_functions.base.create_group_masks | Not checked | In-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.loss_functions.base.soft_rate_computation | Not checked | In-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.loss_functions.counterfactual.CausalFairnessLoss | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.loss_functions.counterfactual.CounterfactualFairnessLoss | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.loss_functions.counterfactual.CounterfactualFairnessLoss.forward | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.loss_functions.counterfactual.IndividualFairnessLoss | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.loss_functions.counterfactual.IndividualFairnessLoss.forward | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.loss_functions.fairness_losses.BoundedGroupLoss | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.loss_functions.fairness_losses.DemographicParityLoss | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.loss_functions.fairness_losses.EqualOpportunityLoss | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.loss_functions.fairness_losses.EqualizedOddsLoss | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.loss_functions.fairness_losses.FairnessAwareBCELoss | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.loss_functions.fairness_losses.FalsePositiveRateParityLoss | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.loss_functions.fairness_losses.create_fairness_loss | Checked | In-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.regularizers.fairness_regularizers.BaseRegularizer | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.regularizers.fairness_regularizers.BaseRegularizer.forward | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.regularizers.fairness_regularizers.BaseRegularizer.get_history | Not checked | In-processing mitigation | method | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.in_processing.regularizers.fairness_regularizers.BaseRegularizer.reset_history | Checked | In-processing mitigation | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.regularizers.fairness_regularizers.ConditionalIndependenceRegularizer | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.regularizers.fairness_regularizers.ConditionalIndependenceRegularizer.forward | Not checked | In-processing mitigation | method | could not be called without a hand-built fixture |
vfairness.in_processing.regularizers.fairness_regularizers.CorrelationPenalty | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.regularizers.fairness_regularizers.CorrelationPenalty.forward | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.regularizers.fairness_regularizers.GroupFairnessRegularizer | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.regularizers.fairness_regularizers.GroupFairnessRegularizer.forward | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.regularizers.fairness_regularizers.HilbertSchmidtRegularizer | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.regularizers.fairness_regularizers.HilbertSchmidtRegularizer.forward | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.regularizers.fairness_regularizers.RegularizerMetrics | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.regularizers.fairness_regularizers.RegularizerMetrics.to_dict | Not checked | In-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.in_processing.regularizers.fairness_regularizers.RegularizerType | Not checked | In-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.in_processing.regularizers.fairness_regularizers.StatisticalParityRegularizer | Checked | In-processing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.regularizers.fairness_regularizers.StatisticalParityRegularizer.forward | Not checked | In-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.regularizers.fairness_regularizers.check_torch_available | Checked | In-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.in_processing.regularizers.fairness_regularizers.create_regularizer | Not checked | In-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifier | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifier.fit | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifier.get_params | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifier.predict | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifier.predict_proba | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifier.predict_with_sensitive_attr | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifier.score | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifier.set_params | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifierResult | Checked | In-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.wrappers.sklearn_wrappers.FairClassifierResult.to_dict | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairRegressor | Checked | In-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairRegressor.fit | Fix pending | In-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.in_processing.wrappers.sklearn_wrappers.FairRegressor.get_params | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.wrappers.sklearn_wrappers.FairRegressor.predict | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairRegressor.predict_with_sensitive_attr | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairRegressor.score | Checked | In-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.in_processing.wrappers.sklearn_wrappers.FairRegressor.set_params | Checked | In-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.wrappers.sklearn_wrappers.make_fair_classifier | Checked | In-processing mitigation | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.in_processing.wrappers.sklearn_wrappers.make_fair_regressor | Checked | In-processing mitigation | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.legal.admissibility.classify_columns | Not checked | Legal | function | called, but the call itself failed, so nothing was learned about it |
vfairness.legal.admissibility.map_domain_to_use_case | Not checked | Legal | function | called, but the call itself failed, so nothing was learned about it |
vfairness.legal.admissibility.map_jurisdiction | Not checked | Legal | function | called, but the call itself failed, so nothing was learned about it |
vfairness.llm._base.RunMetadata | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm._base.RunMetadata.to_dict | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm._base.SerializableMixin | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm._base.SerializableMixin.to_dict | Not checked | LLM fairness testing | method | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.llm._base.SerializableMixin.to_json | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.api_proxy.LLMApiProxy | Not checked | LLM fairness testing | class | could not be constructed without a hand-built fixture |
vfairness.llm.api_proxy.LLMApiProxy.send_batch | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.api_proxy.LLMApiProxy.send_prompt | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.api_proxy.LLMApiProxy.test_connection | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.benchmarks.BenchmarkResult | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.benchmarks.BenchmarkRunner | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.benchmarks.BenchmarkRunner.run_bbq | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.benchmarks.BenchmarkRunner.run_bold | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.benchmarks.BenchmarkRunner.run_holistic_bias | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.benchmarks.benchmark_provenance | Not checked | LLM fairness testing | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.cot_faithfulness.CoTFaithfulnessAnalyzer | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.cot_faithfulness.CoTFaithfulnessAnalyzer.analyze_batch | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.cot_faithfulness.CoTFaithfulnessAnalyzer.analyze_pair | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.cot_faithfulness.CoTFaithfulnessAnalyzer.default_cue_terms | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.cot_faithfulness.CoTFaithfulnessResult | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.cot_faithfulness.FaithfulnessReport | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.counterfactual.CounterfactualResult | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.counterfactual.CounterfactualTester | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.counterfactual.CounterfactualTester.compute_disparity | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.counterfactual.CounterfactualTester.generate_swaps | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.counterfactual.CounterfactualTester.run_test | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.decodingtrust.DecodingTrustRunner | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_adversarial_demonstrations | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_adversarial_robustness | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_all | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_fairness | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_machine_ethics | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_ood_robustness | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_privacy | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_stereotype_bias | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.decodingtrust.DecodingTrustRunner.run_toxicity | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.embedding_bias.EmbeddingBiasDetector | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.embedding_bias.EmbeddingBiasDetector.seat | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.embedding_bias.EmbeddingBiasDetector.weat | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.embedding_bias.WEATResult | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.embedding_bias.WEATResult.to_dict | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.intersectional.IntersectionalAnalyzer | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.intersectional.IntersectionalAnalyzer.analyze | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.intersectional.IntersectionalGroup | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.intersectional.IntersectionalGroup.from_attributes | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.intersectional.IntersectionalResult | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.model_identity.IdentityComparison | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.model_identity.ModelIdentity | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.model_identity.clean_model_name | Checked | LLM fairness testing | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.llm.model_identity.compare_model_identity | Not checked | LLM fairness testing | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.model_identity.describe_model_identity | Not checked | LLM fairness testing | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.model_identity.identity_from_run | Not checked | LLM fairness testing | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.nondeterminism.NoiseProfile | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.nondeterminism.NonDeterminismAnalyzer | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.nondeterminism.NonDeterminismAnalyzer.bootstrap_ci | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.nondeterminism.NonDeterminismAnalyzer.characterize_noise | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.nondeterminism.NonDeterminismAnalyzer.compute_noise_offset | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.nondeterminism.NonDeterminismAnalyzer.equivalence_test | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.nondeterminism.NonDeterminismAnalyzer.is_significant_after_offset | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.nondeterminism.NonDeterminismAnalyzer.required_runs | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.nondeterminism.noise_floor_from_runs | Checked | LLM fairness testing | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.output_analysis.OutputAnalysisResult | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.output_analysis.OutputAnalyzer | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_all | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_framing | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_helpfulness | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_information_quality | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_length | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_llm_judge | Checked | LLM fairness testing | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_refusal_rate | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_regard | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_representation | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_semantic_quality | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_sentiment | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_stereotype | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.output_analysis.OutputAnalyzer.analyze_toxicity | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.paired.mcnemar_paired_test | Not checked | LLM fairness testing | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.paired.sign_flip_paired_test | Not checked | LLM fairness testing | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.paired.usable_binary_pairs | Not checked | LLM fairness testing | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.paired.usable_numeric_pairs | Not checked | LLM fairness testing | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.scorers.ContextualStereotypeScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.ContextualStereotypeScorer.score | Fix pending | LLM fairness testing | method | proved to report, or to claim, something nobody measured |
vfairness.llm.scorers.ContextualStereotypeScorer.score_batch | Checked | LLM fairness testing | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.llm.scorers.FramingScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.FramingScorer.score | Fix pending | LLM fairness testing | method | proved to report, or to claim, something nobody measured |
vfairness.llm.scorers.FramingScorer.score_batch | Checked | LLM fairness testing | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.llm.scorers.HelpfulnessScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.HelpfulnessScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.HelpfulnessScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.InformationQualityScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.InformationQualityScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.InformationQualityScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.KeywordRegardScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.KeywordRegardScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.KeywordRegardScorer.score_batch | Checked | LLM fairness testing | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.llm.scorers.KeywordSentimentScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.KeywordSentimentScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.KeywordSentimentScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.KeywordToxicityScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.KeywordToxicityScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.KeywordToxicityScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.LLMJudgeScorer | Not checked | LLM fairness testing | class | could not be constructed without a hand-built fixture |
vfairness.llm.scorers.LLMJudgeScorer.score | Fix pending | LLM fairness testing | method | proved to report, or to claim, something nobody measured |
vfairness.llm.scorers.LLMJudgeScorer.score_batch | Fix pending | LLM fairness testing | method | proved to report, or to claim, something nobody measured |
vfairness.llm.scorers.PartialCoverageWarning | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.PlaceholderScorerWarning | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.RefusalScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.RefusalScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.RefusalScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.RepresentationScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.RepresentationScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.RepresentationScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.SemanticQualityScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.SemanticQualityScorer.dimension_coverage | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.SemanticQualityScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.SemanticQualityScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.SidecarSentimentScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.SidecarSentimentScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.SidecarSentimentScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.SidecarToxicityScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.SidecarToxicityScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.SidecarToxicityScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.SidecarUnavailableWarning | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.StereotypeScorer | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.StereotypeScorer.score | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.StereotypeScorer.score_batch | Checked | LLM fairness testing | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.TextScorer | Not checked | LLM fairness testing | class | could not be constructed without a hand-built fixture |
vfairness.llm.scorers.TextScorer.score | Checked | LLM fairness testing | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.TextScorer.score_batch | Checked | LLM fairness testing | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.UnscorableTextWarning | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.identifier_tokens | Checked | LLM fairness testing | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.judge_is_subject | Checked | LLM fairness testing | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.mentions_any_term | Checked | LLM fairness testing | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.normalize_text | Checked | LLM fairness testing | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.phrase_present | Checked | LLM fairness testing | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.scorer_provenance | Checked | LLM fairness testing | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.scorers.scorer_status | Checked | LLM fairness testing | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.llm.scorers.term_forms | Checked | LLM fairness testing | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.scorers.word_tokens | Checked | LLM fairness testing | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.text_fairness.GroupScore | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.text_fairness.GroupScore.to_dict | Not checked | LLM fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.llm.text_fairness.TextFairnessAnalyzer | Checked | LLM fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.llm.text_fairness.TextFairnessAnalyzer.analyze | Not checked | LLM fairness testing | method | could not be called without a hand-built fixture |
vfairness.llm.text_fairness.TextFairnessResult | Checked | LLM fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.llm.text_fairness.TextFairnessResult.to_dict | Not checked | LLM fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.mcp.server.analyze_intersectional | Not checked | MCP tools | function | called, but the call itself failed, so nothing was learned about it |
vfairness.mcp.server.audit_agent | Not checked | MCP tools | function | called, but the call itself failed, so nothing was learned about it |
vfairness.mcp.server.detect_proxies | Not checked | MCP tools | function | called, but the call itself failed, so nothing was learned about it |
vfairness.mcp.server.explain_decision | Not checked | MCP tools | function | called, but the call itself failed, so nothing was learned about it |
vfairness.mcp.server.explain_in_plain_language | Not checked | MCP tools | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.mcp.server.fairness_triage | Not checked | MCP tools | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.mcp.server.glossary | Not checked | MCP tools | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.mcp.server.legal_framing | Not checked | MCP tools | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.mcp.server.main | Checked | MCP tools | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.mcp.server.measure_fairness | Not checked | MCP tools | function | called, but the call itself failed, so nothing was learned about it |
vfairness.mcp.server.suggest_mitigation | Not checked | MCP tools | function | called, but the call itself failed, so nothing was learned about it |
vfairness.mcp.server.triage_dataset | Not checked | MCP tools | function | called, but the call itself failed, so nothing was learned about it |
vfairness.mcp.tools.analyze_intersectional | Checked | MCP tools | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.mcp.tools.audit_agent | Checked | MCP tools | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.mcp.tools.detect_proxies | Fix pending | MCP tools | function | proved to report, or to claim, something nobody measured |
vfairness.mcp.tools.explain_decision | Fix pending | MCP tools | function | proved to report, or to claim, something nobody measured |
vfairness.mcp.tools.glossary_markdown | Checked | MCP tools | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.mcp.tools.jsonify | Fix pending | MCP tools | function | proved to report, or to claim, something nobody measured |
vfairness.mcp.tools.jurisdictions_markdown | Checked | MCP tools | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.mcp.tools.load_dataframe | Checked | MCP tools | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.mcp.tools.measure_fairness | Checked | MCP tools | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.mcp.tools.suggest_mitigation | Fix pending | MCP tools | function | proved to report, or to claim, something nobody measured |
vfairness.mcp.tools.triage_dataset | Fix pending | MCP tools | function | proved to report, or to claim, something nobody measured |
vfairness.multi_agent.collusion.AdversarialCollusionDetector | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.multi_agent.collusion.AdversarialCollusionDetector.analyze | Not checked | Agent fairness testing | method | could not be called without a hand-built fixture |
vfairness.multi_agent.collusion.CollusionResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.multi_agent.compositionality.CompositionalityAnalyzer | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.multi_agent.compositionality.CompositionalityAnalyzer.analyze | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.compositionality.CompositionalityResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.multi_agent.delegation.DelegationResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.multi_agent.delegation.DelegationRoutingAuditor | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.multi_agent.delegation.DelegationRoutingAuditor.analyze | Not checked | Agent fairness testing | method | could not be called without a hand-built fixture |
vfairness.multi_agent.emergent.EmergentBiasDetector | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.multi_agent.emergent.EmergentBiasDetector.analyze | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.emergent.EmergentBiasResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.multi_agent.groupthink.GroupthinkDetector | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.multi_agent.groupthink.GroupthinkDetector.analyze_convergence | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.groupthink.GroupthinkDetector.detect_coalitions | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.groupthink.GroupthinkResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.multi_agent.harness.HarnessTrace | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.multi_agent.harness.MultiAgentRunHarness | Checked | Agent fairness testing | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.multi_agent.harness.MultiAgentRunHarness.as_collusion_inputs | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.harness.MultiAgentRunHarness.as_compositionality_input | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.harness.MultiAgentRunHarness.as_delegation_inputs | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.harness.MultiAgentRunHarness.as_emergent_inputs | Not checked | Agent fairness testing | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.multi_agent.harness.MultiAgentRunHarness.as_negotiation_inputs | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.harness.MultiAgentRunHarness.record_routing | Checked | Agent fairness testing | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.multi_agent.harness.MultiAgentRunHarness.record_sample | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.harness.MultiAgentRunHarness.record_turn | Checked | Agent fairness testing | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.multi_agent.harness.MultiAgentRunHarness.system_bias | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.negotiation.NegotiationFairnessTracker | Checked | Agent fairness testing | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.multi_agent.negotiation.NegotiationFairnessTracker.analyze | Not checked | Agent fairness testing | method | called, but the call itself failed, so nothing was learned about it |
vfairness.multi_agent.negotiation.NegotiationResult | Checked | Agent fairness testing | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.net.egress.GuardedSession | Checked | Networking | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.net.egress.GuardedSession.close | Checked | Networking | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.net.egress.GuardedSession.get_adapter | Not checked | Networking | method | called, but the call itself failed, so nothing was learned about it |
vfairness.net.egress.PinnedIPAdapter | Not checked | Networking | class | could not be constructed without a hand-built fixture |
vfairness.net.egress.PinnedIPAdapter.init_poolmanager | Not checked | Networking | method | could not be called without a hand-built fixture |
vfairness.net.egress.PinnedIPAdapter.send | Not checked | Networking | method | could not be called without a hand-built fixture |
vfairness.net.egress.SSRFError | Checked | Networking | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.net.egress.guarded_post | Not checked | Networking | function | called, but the call itself failed, so nothing was learned about it |
vfairness.net.egress.validate_endpoint | Not checked | Networking | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.causal.attribute.AttributionResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.attribute.AttributionResult.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.causal.attribute.NodeContribution | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.attribute.attribute_distribution_change | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.counterfactual.CounterfactualResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.counterfactual.CounterfactualResult.to_dict | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.counterfactual.compute_counterfactual | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.graph.CausalFairnessGraph | Checked | Operations (other) | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.causal.graph.CausalFairnessGraph.add_edge | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.causal.graph.CausalFairnessGraph.add_variable | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.graph.CausalFairnessGraph.discrimination_paths | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.graph.CausalFairnessGraph.has_direct_discrimination | Checked | Operations (other) | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.causal.graph.CausalFairnessGraph.not_assessable | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.graph.CausalFairnessGraph.outcome_nodes | Not checked | Operations (other) | method | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.operations.causal.graph.CausalFairnessGraph.protected_nodes | Not checked | Operations (other) | method | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.operations.causal.graph.CausalFairnessGraph.summary | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.graph.CausalFairnessGraph.to_gml | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.graph.DiscriminationPath | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.graph.DiscriminationPath.to_dict | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.identify.IdentificationResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.identify.IdentificationResult.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.causal.identify.PathIdentification | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.identify.identify_paths | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.causal.mediate.MediationDecomposition | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.mediate.MediationResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.mediate.MediationResult.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.causal.mediate.decompose_mediation | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.causal.refute.RefutationOutcome | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.refute.RefutationResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.causal.refute.RefutationResult.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.causal.refute.run_refutation_suite | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.task_handlers.handle_attribute | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.task_handlers.handle_counterfactual | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.task_handlers.handle_identify | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.task_handlers.handle_mediate | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.task_handlers.handle_refute | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.causal.task_handlers.load_dataset_from_payload | Checked | Operations (other) | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.causal.task_handlers.main | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.FairnessReportCard | Checked | CI/CD gates | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.cicd.gate.FairnessReportCard.to_dict | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.FairnessReportCard.to_github_comment_payload | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.FairnessReportCard.to_markdown | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.GateConfig | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.gate.GateConfig.to_dict | Not checked | CI/CD gates | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.gate.GateDecision | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.gate.GateDecision.to_dict | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.GateDecision.to_markdown_report | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.GateStatus | Not checked | CI/CD gates | class | could not be constructed without a hand-built fixture |
vfairness.operations.cicd.gate.HierarchicalGateConfig | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.gate.HierarchicalGateConfig.to_dict | Not checked | CI/CD gates | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.gate.IntersectionalGateDecision | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.gate.IntersectionalGateDecision.to_dict | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.IntersectionalGateDecision.to_markdown_report | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.MetricEvaluation | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.gate.MetricEvaluation.to_dict | Not checked | CI/CD gates | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.gate.ModelFairnessGate | Checked | CI/CD gates | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.gate.ModelFairnessGate.create_github_check | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.ModelFairnessGate.evaluate | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.ModelFairnessGate.evaluate_from_metrics | Not checked | CI/CD gates | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.gate.ModelFairnessGate.evaluate_hierarchical | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.ModelFairnessGate.get_explanation | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.gate.SmallSampleWarning | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.gate.SmallSampleWarning.to_dict | Not checked | CI/CD gates | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.monitor.AlertSeverity | Not checked | CI/CD gates | class | could not be constructed without a hand-built fixture |
vfairness.operations.cicd.monitor.BiasMonitor | Checked | CI/CD gates | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.monitor.BiasMonitor.drift_detected | Checked | CI/CD gates | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.cicd.monitor.BiasMonitor.get_alerts | Checked | CI/CD gates | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.monitor.BiasMonitor.get_current_metrics | Checked | CI/CD gates | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.monitor.BiasMonitor.get_drift_status | Checked | CI/CD gates | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.monitor.BiasMonitor.get_rolling_average | Fix pending | CI/CD gates | method | proved to report, or to claim, something nobody measured |
vfairness.operations.cicd.monitor.BiasMonitor.get_summary | Checked | CI/CD gates | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.monitor.BiasMonitor.log_batch | Checked | CI/CD gates | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.monitor.BiasMonitor.reset | Checked | CI/CD gates | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.monitor.BiasMonitor.to_prometheus_metrics | Checked | CI/CD gates | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.monitor.BiasMonitor.trigger_alert | Checked | CI/CD gates | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.monitor.BiasMonitor.unmeasurable_metrics | Checked | CI/CD gates | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.monitor.BiasMonitor.update_baseline | Checked | CI/CD gates | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.monitor.DriftAlert | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.monitor.DriftAlert.to_dict | Checked | CI/CD gates | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.cicd.monitor.DriftType | Not checked | CI/CD gates | class | could not be constructed without a hand-built fixture |
vfairness.operations.cicd.monitor.MonitorConfig | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.monitor.MonitorConfig.to_dict | Checked | CI/CD gates | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.monitor.MonitoringResult | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.monitor.MonitoringResult.to_dict | Checked | CI/CD gates | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.precommit.check_fairness_config | Not checked | CI/CD gates | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.operations.cicd.precommit.check_model_card | Checked | CI/CD gates | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.cicd.precommit.main | Not checked | CI/CD gates | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.quality_report.build_quality_report | Not checked | CI/CD gates | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.task_handlers.handle_data_validation | Not checked | CI/CD gates | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.task_handlers.main | Not checked | CI/CD gates | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.testing.FairnessAssertionError | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.testing.FairnessTestResult | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.testing.FairnessTestResult.to_dict | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.testing.FairnessTestSuite | Checked | CI/CD gates | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.testing.FairnessTestSuite.get_summary | Not checked | CI/CD gates | method | could not be called without a hand-built fixture |
vfairness.operations.cicd.testing.FairnessTestSuite.test_model | Not checked | CI/CD gates | method | could not be called without a hand-built fixture |
vfairness.operations.cicd.testing.FairnessTestSuite.test_predictions | Not checked | CI/CD gates | method | could not be called without a hand-built fixture |
vfairness.operations.cicd.testing.FairnessTestSuite.to_junit_xml | Not checked | CI/CD gates | method | could not be called without a hand-built fixture |
vfairness.operations.cicd.testing.TestStatus | Not checked | CI/CD gates | class | could not be constructed without a hand-built fixture |
vfairness.operations.cicd.testing.assert_fairness | Not checked | CI/CD gates | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.testing.fairness_test | Not checked | CI/CD gates | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.testing.parametrize_fairness | Not checked | CI/CD gates | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.validator.DataBiasValidator | Checked | CI/CD gates | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.cicd.validator.DataBiasValidator.get_explanation | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.validator.DataBiasValidator.validate | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.validator.DataBiasValidator.validate_batch | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.validator.DataValidationConfig | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.validator.DataValidationConfig.to_dict | Not checked | CI/CD gates | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.validator.DataValidationResult | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.validator.DataValidationResult.execution_coverage | Not checked | CI/CD gates | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.cicd.validator.DataValidationResult.to_dict | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.validator.DataValidationResult.to_junit_xml | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.validator.ValidationIssue | Checked | CI/CD gates | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.cicd.validator.ValidationIssue.to_dict | Not checked | CI/CD gates | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.cicd.validator.ValidationSeverity | Not checked | CI/CD gates | class | could not be constructed without a hand-built fixture |
vfairness.operations.experimentation.analysis.CausalDecomposition | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.analysis.CausalDecomposition.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ExperimentAnalysis | Checked | Operations (other) | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.analysis.ExperimentAnalysis.compute_pareto_frontier | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ExperimentAnalysis.decision_recommendation | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ExperimentAnalysis.heterogeneous_treatment_effects | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ExperimentAnalysis.mediation_analysis | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ExperimentAnalysis.spillover_detection | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ExperimentAnalysis.temporal_stability_check | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ExperimentAnalysis.to_report_sections | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ExperimentRecommendation | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.analysis.ExperimentRecommendation.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.analysis.ParetoPoint | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.analysis.ParetoPoint.to_dict | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.experimentation.analysis.RecommendationDecision | Not checked | Operations (other) | class | could not be constructed without a hand-built fixture |
vfairness.operations.experimentation.analysis.TemporalStabilityResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.analysis.TemporalStabilityResult.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.experiment.DesignType | Not checked | Operations (other) | class | could not be constructed without a hand-built fixture |
vfairness.operations.experimentation.experiment.ExperimentConfig | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.experiment.ExperimentResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.experiment.ExperimentResult.save | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.experiment.ExperimentResult.to_dataframe | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.experiment.ExperimentResult.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.experiment.FairnessExperiment | Checked | Operations (other) | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.experiment.FairnessExperiment.calculate_intersectional_power | Not checked | Operations (other) | method | could not be called without a hand-built fixture |
vfairness.operations.experimentation.experiment.FairnessExperiment.detect_heterogeneous_effects | Not checked | Operations (other) | method | could not be called without a hand-built fixture |
vfairness.operations.experimentation.experiment.FairnessExperiment.get_summary | Not checked | Operations (other) | method | could not be called without a hand-built fixture |
vfairness.operations.experimentation.experiment.FairnessExperiment.run_full_analysis | Not checked | Operations (other) | method | could not be called without a hand-built fixture |
vfairness.operations.experimentation.experiment.FairnessExperiment.to_dataframe | Not checked | Operations (other) | method | could not be called without a hand-built fixture |
vfairness.operations.experimentation.experiment.IntersectionEffect | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.experiment.IntersectionEffect.to_dict | Not checked | Operations (other) | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.experiment.assign_clusters | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.experiment.create_factorial_design | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.experimentation.power.FairnessPowerAnalyzer | Checked | Operations (other) | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.FairnessPowerAnalyzer.adaptive_sampling_plan | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.FairnessPowerAnalyzer.get_detailed_results | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.FairnessPowerAnalyzer.get_power_summary | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.FairnessPowerAnalyzer.minimum_detectable_effect | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.FairnessPowerAnalyzer.power_for_sample_size | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.FairnessPowerAnalyzer.required_sample_size | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.FairnessPowerAnalyzer.sequential_test | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.PowerConfig | Not checked | Operations (other) | class | could not be constructed without a hand-built fixture |
vfairness.operations.experimentation.power.PowerResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.power.PowerResult.to_dict | Checked | Operations (other) | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.experimentation.power.SPRTDecision | Not checked | Operations (other) | class | could not be constructed without a hand-built fixture |
vfairness.operations.experimentation.power.SamplingPlan | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.power.SamplingPlan.to_dataframe | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.SamplingPlan.to_dict | Checked | Operations (other) | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.experimentation.power.SequentialTestResult | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.experimentation.power.SequentialTestResult.to_dict | Checked | Operations (other) | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.monitoring.alerts.AdaptiveThresholdManager | Checked | Monitoring | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.AdaptiveThresholdManager.get_all_thresholds | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.alerts.AdaptiveThresholdManager.get_feedback_stats | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.AdaptiveThresholdManager.get_threshold | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.alerts.AdaptiveThresholdManager.is_alert_warranted | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.AdaptiveThresholdManager.reset | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.alerts.AdaptiveThresholdManager.set_threshold | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.alerts.AdaptiveThresholdManager.update_from_feedback | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.AlertPayload | Checked | Monitoring | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.alerts.AlertPayload.acknowledge | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.alerts.AlertPayload.to_dict | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.FairnessAlertPrioritizer | Checked | Monitoring | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.FairnessAlertPrioritizer.build_drift_event | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.FairnessAlertPrioritizer.calculate_priority | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.FairnessAlertPrioritizer.clear_log | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.alerts.FairnessAlertPrioritizer.create_alert | Fix pending | Monitoring | method | proved to report, or to claim, something nobody measured |
vfairness.operations.monitoring.alerts.FairnessAlertPrioritizer.get_alert_log | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.FairnessAlertPrioritizer.get_alert_summary | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.alerts.FairnessAlertPrioritizer.route_alert | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.DriftResult | Checked | Monitoring | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.drift.DriftResult.to_dict | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector | Checked | Monitoring | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector.check_drift | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector.clear_history | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.drift.FairnessDriftDetector.decompose_temporal_patterns | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector.detect_drift_ks | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector.detect_drift_mmd | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector.detect_drift_multiscale | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector.get_explanation | Checked | Monitoring | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.monitoring.drift.FairnessDriftDetector.get_history_df | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector.get_results_history | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.drift.FairnessDriftDetector.run_sprt | Fix pending | Monitoring | method | proved to report, or to claim, something nobody measured |
vfairness.operations.monitoring.drift.FairnessDriftDetector.set_baseline | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.drift.MultiscaleDriftResult | Checked | Monitoring | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.drift.MultiscaleDriftResult.to_dict | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.sequential.cusum_drift | Not checked | Monitoring | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.monitoring.sequential.page_hinkley | Not checked | Monitoring | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.monitoring.sequential.sequential_fairness_drift | Not checked | Monitoring | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.monitoring.tracker.FairnessMonitor | Checked | Monitoring | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.FairnessMonitor.compute_demographic_parity | Checked | Monitoring | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.monitoring.tracker.FairnessMonitor.compute_disparate_impact | Checked | Monitoring | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.monitoring.tracker.FairnessMonitor.compute_equal_opportunity | Fix pending | Monitoring | method | proved to report, or to claim, something nobody measured |
vfairness.operations.monitoring.tracker.FairnessMonitor.compute_equalized_odds | Fix pending | Monitoring | method | proved to report, or to claim, something nobody measured |
vfairness.operations.monitoring.tracker.FairnessMonitor.get_alert_summary | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.FairnessMonitor.get_current_metrics | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.FairnessMonitor.get_explanation | Fix pending | Monitoring | method | proved to report, or to claim, something nobody measured |
vfairness.operations.monitoring.tracker.FairnessMonitor.get_metric_history | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.FairnessMonitor.get_window_df | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.tracker.FairnessMonitor.reset | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.tracker.FairnessMonitor.set_reference | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.tracker.FairnessMonitor.update_and_check | Fix pending | Monitoring | method | proved to report, or to claim, something nobody measured |
vfairness.operations.monitoring.tracker.FairnessMonitorConfig | Checked | Monitoring | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer | Checked | Monitoring | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.detect_seasonal_pattern | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.detect_trend | Fix pending | Monitoring | method | proved to report, or to claim, something nobody measured |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.detect_weekly_degradation | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.forecast_metric | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.get_explanation | Fix pending | Monitoring | method | proved to report, or to claim, something nobody measured |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.get_metric_summary | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.get_tracked_metrics | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.to_dataframe | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.tracker.TemporalFairnessAnalyzer.update_daily_metrics | Checked | Monitoring | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.tracker.WindowMetrics | Checked | Monitoring | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.monitoring.tracker.WindowMetrics.to_dict | Checked | Monitoring | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.monitoring.tracker.mmd_gaussian | Fix pending | Monitoring | function | proved to report, or to claim, something nobody measured |
vfairness.operations.pulse.agent_probe.agent_probe_pulse | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.causal_skeleton.CausalSkeleton | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.pulse.causal_skeleton.CausalSkeleton.to_dict | Not checked | Operations (other) | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.causal_skeleton.build_causal_skeleton | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.causal_skeleton.domain_dag_template | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.llm_probe.apply_bh | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.pulse.llm_probe.correct_families | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.pulse.llm_probe.llm_probe_pulse | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.orchestrator.build_legal_framework_block | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.pulse.orchestrator.build_scope_block | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.orchestrator.run_pulse | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.pipeline.PulsePipelineInputs | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.pulse.pipeline.run_pulse_pipeline | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.pulse.recommend.recommend_fairness_definition | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.pulse.recommend.recommend_interventions | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.regulatory.attach_lightweight_regulatory | Fix pending | Operations (other) | function | proved to report, or to claim, something nobody measured |
vfairness.operations.pulse.regulatory.base_rates_differ | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.build_art10 | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.build_ll144 | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.build_recheck | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.build_reference_groups | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.build_regulatory_exports | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.build_targets | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.clamp_target_ratio | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.empty_exports | Fix pending | Operations (other) | function | proved to report, or to claim, something nobody measured |
vfairness.operations.pulse.regulatory.historical_context | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.iso24027_crosswalk | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.legal_admissibility | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.regulatory.legal_context_as_of | Checked | Operations (other) | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.pulse.regulatory.parse_pulse_options | Checked | Operations (other) | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.pulse.regulatory.sanitize_suite | Checked | Operations (other) | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.pulse.regulatory.uncovered_admissibility | Checked | Operations (other) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.pulse.scoring.score_model_over_frame | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.task_handlers.handle_pulse_run | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.task_handlers.main | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.pulse.traces.MalformedTraceExportWarning | Checked | Operations (other) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.pulse.traces.ingest_and_run_pulse | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.pulse.traces.maybe_flatten_spans | Checked | Operations (other) | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.pulse.traces.parse_trace_export | Not checked | Operations (other) | function | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.operations.pulse.vision_probe.vision_probe_pulse | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.compliance.AdverseActionReasons | Not checked | Reporting | class | constructed on healthy and degenerate input; it derives a number and that has not been judged yet |
vfairness.operations.reporting.compliance.build_assurance_verdict | Not checked | Reporting | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.compliance.compute_adverse_action_reasons | Not checked | Reporting | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.compliance.compute_signed_test_log | Not checked | Reporting | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.compliance.generate_annex_iv_data | Checked | Reporting | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.compliance.generate_dpia_sections | Checked | Reporting | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.compliance.generate_iso42001_evidence_map | Not checked | Reporting | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.compliance.generate_model_card | Checked | Reporting | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.compliance.generate_risk_register_from_audit | Checked | Reporting | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.dashboard.DashboardConfig | Checked | Reporting | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.dashboard.FairnessDashboard | Checked | Reporting | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_alert_summary | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_disparity_comparison | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_drift_timeline | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_executive_view | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_health_score_gauge | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_intersectional_heatmap | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_operational_view | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_subgroup_sunburst | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_technical_view | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.create_trend_analysis | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.get_explanation | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.FairnessDashboard.to_html | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.dashboard.TimeWindow | Not checked | Reporting | class | could not be constructed without a hand-built fixture |
vfairness.operations.reporting.interactive.InteractiveConfig | Checked | Reporting | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.interactive.InteractiveDashboard | Checked | Reporting | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.interactive.InteractiveDashboard.create_dash_app | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.interactive.InteractiveDashboard.get_capabilities | Not checked | Reporting | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.reporting.interactive.InteractiveDashboard.run | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.interactive.InteractiveDashboard.save_html | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.interactive.InteractiveDashboard.simulate_threshold_change | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.interactive.InteractiveDashboard.to_standalone_html | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.interactive.simulate_threshold_change | Not checked | Reporting | function | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.GeneratedReport | Checked | Reporting | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.reports.GeneratedReport.save | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.GeneratedReport.to_dict | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.OutputFormat | Not checked | Reporting | class | could not be constructed without a hand-built fixture |
vfairness.operations.reporting.reports.ReportConfig | Checked | Reporting | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.reports.ReportGenerator | Checked | Reporting | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.reports.ReportGenerator.generate | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.ReportGenerator.generate_alert_report | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.ReportGenerator.generate_drift_report | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.ReportGenerator.generate_executive_report | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.ReportGenerator.generate_operational_report | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.ReportGenerator.generate_technical_report | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.ReportGenerator.generate_threshold_breach_report | Not checked | Reporting | method | called, but the call itself failed, so nothing was learned about it |
vfairness.operations.reporting.reports.ReportTier | Not checked | Reporting | class | could not be constructed without a hand-built fixture |
vfairness.operations.reporting.store.HealthScore | Checked | Reporting | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.HealthScore.to_dict | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore | Checked | Reporting | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.clear | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.compute_health_score | Fix pending | Reporting | method | proved to report, or to claim, something nobody measured |
vfairness.operations.reporting.store.MetricsStore.get_alerts | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.get_drift_history | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.get_groups | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.get_latest | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.get_metric_names | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.get_metrics | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.get_sources | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.get_summary | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.get_threshold_history | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.get_time_range | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.ingest_alert | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.ingest_dataframe | Fix pending | Reporting | method | proved to report, or to claim, something nobody measured |
vfairness.operations.reporting.store.MetricsStore.ingest_drift_result | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.ingest_from_analyzer | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.ingest_from_detector | Checked | Reporting | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.reporting.store.MetricsStore.ingest_from_monitor | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStore.ingest_from_prioritizer | Checked | Reporting | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.operations.reporting.store.MetricsStore.ingest_threshold_update | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.ingest_window_metrics | Fix pending | Reporting | method | proved to report, or to claim, something nobody measured |
vfairness.operations.reporting.store.MetricsStore.prune | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.register_model | Checked | Reporting | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.MetricsStore.to_dataframe | Checked | Reporting | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.operations.reporting.store.MetricsStoreConfig | Checked | Reporting | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.reporting.store.PrivacyLevel | Not checked | Reporting | class | could not be constructed without a hand-built fixture |
vfairness.operations.reporting.store.StoredMetricRecord | Checked | Reporting | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.operations.validity.task_handlers.handle_validity_run | Not checked | Operations (other) | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.operations.validity.task_handlers.main | Not checked | Operations (other) | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_calibration_comparison | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_calibration_disparity | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_confidence_intervals | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_effect_sizes | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_fairness_metrics | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_fairness_report | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_group_calibration | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_group_comparison | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_group_disparity_heatmap | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_metrics_radar | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_reliability_diagram | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.plot_tradeoff_curve | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.analyze_disparity | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.analyze_tradeoffs | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.calibrate | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.clear_cache | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.decompose_brier | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.evaluate_brier | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.evaluate_calibration | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.evaluate_calibration_improvement | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.evaluate_ece | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.evaluate_mce | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.fit_calibrator | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.full_analysis | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.get_calibration_curve | Checked | Post-processing mitigation | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.get_calibration_result | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.get_data_summary | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.get_explanation | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.get_impossibility_diagnosis | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.get_recommendation | Checked | Post-processing mitigation | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.calibration.analyzer.CalibrationAnalyzer.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationReport | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.analyzer.CalibrationReport.summary | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationReport.to_dict | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationReport.to_json | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.analyzer.CalibrationReport.to_svg | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrationResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrationResult.to_dict | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrator | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrator.evaluate | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrator.fit | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrator.fit_transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrator.get_calibration_result | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrator.get_group_calibrator | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.GroupCalibrator.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.IntersectionalCalibrator | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.IntersectionalCalibrator.fit | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.IntersectionalCalibrator.fit_transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.IntersectionalCalibrator.get_calibrator_for_group | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.IntersectionalCalibrator.get_group_provenance | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.IntersectionalCalibrator.get_group_statistics | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.IntersectionalCalibrator.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.group_calibrator.IntersectionalProvenanceWarning | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.group_calibrator.UnknownGroupWarning | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.group_calibrator.UnmeasurableGroupWarning | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.group_calibrator.validate_borrowing_strategy | Checked | Post-processing mitigation | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.group_calibrator.validate_fallback_strategy | Checked | Post-processing mitigation | function | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.methods.BaseCalibrator | Not checked | Post-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.post_processing.calibration.methods.BaseCalibrator.fit | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.methods.BaseCalibrator.fit_transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.BaseCalibrator.transform | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.methods.BetaCalibrator | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.BetaCalibrator.fit | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.BetaCalibrator.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.CalibrationFitResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.methods.CalibrationFitResult.to_dict | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.methods.CalibrationMethod | Not checked | Post-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.post_processing.calibration.methods.HistogramBinning | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.HistogramBinning.fit | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.HistogramBinning.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.IsotonicCalibrator | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.IsotonicCalibrator.fit | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.calibration.methods.IsotonicCalibrator.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.PlattScaling | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.PlattScaling.fit | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.PlattScaling.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.TemperatureScaling | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.TemperatureScaling.fit | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.calibration.methods.TemperatureScaling.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.methods.create_calibrator | Checked | Post-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.calibration.metrics.BrierDecomposition | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.metrics.BrierDecomposition.to_dict | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.metrics.CalibrationCurveResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.metrics.CalibrationCurveResult.to_dict | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.metrics.CalibrationDisparityResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.metrics.CalibrationDisparityResult.to_dict | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.metrics.CalibrationMetricResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.metrics.CalibrationMetricResult.to_dict | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.metrics.IntegratedCalibrationResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.metrics.IntegratedCalibrationResult.to_dict | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.metrics.MulticalibrationResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.metrics.MulticalibrationResult.to_dict | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.metrics.brier_score | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.metrics.brier_score_decomposition | Checked | Post-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.calibration.metrics.calibration_curve | Checked | Post-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.calibration.metrics.calibration_disparity | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.metrics.calibration_in_the_large | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.metrics.calibration_slope | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.metrics.cv_calibration_stability | Not checked | Post-processing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.metrics.ece_confidence_intervals | Not checked | Post-processing mitigation | function | executed, and on 1 world(s) where nothing was measurable (empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.post_processing.calibration.metrics.expected_calibration_error | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.metrics.group_calibration_metrics | Checked | Post-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.calibration.metrics.integrated_calibration_index | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.metrics.integrated_calibration_index_with_ci | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.metrics.maximum_calibration_error | Checked | Post-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.calibration.metrics.multicalibration | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.calibration.metrics.multicalibration_with_ci | Checked | Post-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.calibration.metrics.per_group_brier_decomposition | Not checked | Post-processing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.metrics.sufficiency_test | Not checked | Post-processing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.tradeoffs.CalibrationRecommendation | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.tradeoffs.CalibrationRecommendation.to_dict | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.tradeoffs.ParetoPoint | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.tradeoffs.ParetoPoint.dominates | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.tradeoffs.TradeoffAnalysisResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.calibration.tradeoffs.TradeoffAnalysisResult.to_dict | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.tradeoffs.analyze_calibration_fairness_tradeoff | Not checked | Post-processing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.tradeoffs.calibration_vs_error_parity | Not checked | Post-processing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.tradeoffs.compute_pareto_frontier | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.tradeoffs.impossibility_diagnostics | Not checked | Post-processing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.tradeoffs.mitigation_pareto | Not checked | Post-processing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.tradeoffs.recommend_calibration_strategy | Not checked | Post-processing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.calibration.visualization.create_calibration_dashboard | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.visualization.plot_calibration_comparison | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.visualization.plot_calibration_disparity | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.visualization.plot_group_calibration | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.visualization.plot_pareto_frontier | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.visualization.plot_reliability_diagram | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.calibration.visualization.plot_tradeoff_curve | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.ranking.rerank.exposure_parity_rerank | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.reweighting.analyzer.ReweightingAnalysisReport | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.reweighting.analyzer.ReweightingAnalysisReport.summary | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.reweighting.analyzer.ReweightingAnalysisReport.to_dict | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.reweighting.analyzer.ReweightingAnalyzer | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.analyzer.ReweightingAnalyzer.analyze_method | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.reweighting.analyzer.ReweightingAnalyzer.compare_methods | Not checked | Post-processing mitigation | method | executed, and on 1 world(s) where nothing was measurable (empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.post_processing.reweighting.analyzer.ReweightingAnalyzer.full_analysis | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.reweighting.analyzer.ReweightingAnalyzer.get_explanation | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.reweighting.analyzer.ReweightingImpactResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.reweighting.analyzer.ReweightingImpactResult.to_dict | Not checked | Post-processing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.post_processing.reweighting.reweighter.BaseReweighter | Not checked | Post-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.post_processing.reweighting.reweighter.BaseReweighter.fit | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.reweighting.reweighter.BaseReweighter.fit_transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.BaseReweighter.predict | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.reweighting.reweighter.BaseReweighter.transform | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.reweighting.reweighter.CalibratedEqualizer | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.CalibratedEqualizer.fit | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.reweighting.reweighter.CalibratedEqualizer.transform | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.reweighting.reweighter.DistributionMatcher | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.DistributionMatcher.fit | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.reweighting.reweighter.DistributionMatcher.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.PredictionReweighter | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.PredictionReweighter.fit | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.PredictionReweighter.transform | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.RejectionOptionClassifier | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.RejectionOptionClassifier.fit | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.RejectionOptionClassifier.predict | Checked | Post-processing mitigation | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.reweighting.reweighter.RejectionOptionClassifier.transform | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.reweighting.reweighter.ReweightingMethod | Not checked | Post-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.post_processing.reweighting.reweighter.ReweightingResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.reweighting.reweighter.ReweightingResult.summary | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.ReweightingResult.to_dict | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.reweighting.reweighter.create_reweighter | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.analyzer.FeasibleRegion | Not checked | Post-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalysisReport | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalysisReport.summary | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalysisReport.to_dict | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalyzer | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalyzer.analyze_threshold | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalyzer.analyze_threshold_range | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalyzer.find_feasible_region | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalyzer.find_optimal_threshold | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalyzer.full_analysis | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdAnalyzer.get_explanation | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdImpactResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.analyzer.ThresholdImpactResult.to_dict | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.constraints.ConstraintViolation | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.constraints.ConstraintViolation.to_dict | Not checked | Post-processing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.constraints.FairnessConstraintType | Not checked | Post-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.post_processing.threshold_optimization.constraints.FeasibleThresholds | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.constraints.compute_constraint_violation | Not checked | Post-processing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.post_processing.threshold_optimization.constraints.find_feasible_thresholds | Checked | Post-processing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.BaseThresholdOptimizer | Not checked | Post-processing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.post_processing.threshold_optimization.optimizer.BaseThresholdOptimizer.fit | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.optimizer.BaseThresholdOptimizer.fit_predict | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.BaseThresholdOptimizer.predict | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.optimizer.GroupThresholdOptimizer | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.GroupThresholdOptimizer.fit | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.threshold_optimization.optimizer.GroupThresholdOptimizer.predict | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.MultiObjectiveThresholdOptimizer | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.MultiObjectiveThresholdOptimizer.fit | Fix pending | Post-processing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.post_processing.threshold_optimization.optimizer.MultiObjectiveThresholdOptimizer.predict | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.MultiObjectiveThresholdOptimizer.select_point | Checked | Post-processing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.optimizer.ThresholdConstraint | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.optimizer.ThresholdOptimizer | Checked | Post-processing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.ThresholdOptimizer.fit | Checked | Post-processing mitigation | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.post_processing.threshold_optimization.optimizer.ThresholdOptimizer.predict | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.ThresholdResult | Checked | Post-processing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.post_processing.threshold_optimization.optimizer.ThresholdResult.summary | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.ThresholdResult.to_dict | Checked | Post-processing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.post_processing.threshold_optimization.optimizer.create_threshold_optimizer | Checked | Post-processing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport | Checked | Bias detection | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.assessment_coverage | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.empty_is_not_a_measurement | Not checked | Bias detection | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.execution_coverage | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.get_critical_count | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.get_high_risk_features | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.summary | Checked | Bias detection | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.to_dict | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.to_json | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.to_svg | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasAuditReport.unassessable_attributes | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasDetector | Checked | Bias detection | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasDetector.analyze_disparities | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasDetector.clear_cache | Checked | Bias detection | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.detector.BiasDetector.detect_historical_patterns | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasDetector.detect_representation_bias | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasDetector.full_audit | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasDetector.get_dataset_summary | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasDetector.get_explanation | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.detector.BiasDetector.identify_proxies | Checked | Bias detection | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.geographic_data.GeographicRiskAssessment | Checked | Bias detection | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.geographic_data.HOLCAreaInfo | Checked | Bias detection | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.geographic_data.HOLCGrade | Not checked | Bias detection | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.bias_detection.geographic_data.assess_geographic_feature_risk | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.geographic_data.fetch_holc_data | Checked | Bias detection | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.geographic_data.get_available_holc_cities | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.geographic_data.get_holc_risk_level | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.geographic_data.get_svi_data_url | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.geographic_data.lookup_holc_grade_by_zip | Checked | Bias detection | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.geographic_data.parse_holc_grade | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.geographic_data.print_data_quality_notes | Checked | Bias detection | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.historical.HistoricalPatternResult | Checked | Bias detection | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.historical.HistoricalPatternResult.to_dict | Not checked | Bias detection | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.bias_detection.historical.HistoricalRiskLevel | Not checked | Bias detection | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.bias_detection.historical.attribute_historical_pattern | Checked | Bias detection | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.historical.check_geographic_redlining_risk | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.historical.detect_historical_patterns | Checked | Bias detection | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.historical.domain_historical_context | Checked | Bias detection | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.proxy.MultivariateProxyResult | Checked | Bias detection | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.proxy.MultivariateProxyResult.to_dict | Not checked | Bias detection | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.proxy.MultivariateProxyResult.was_assessed | Not checked | Bias detection | method | executed, and on 8 world(s) where nothing was measurable (all_nan_scores, constant_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.preprocessing.bias_detection.proxy.ProxyRiskLevel | Not checked | Bias detection | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.bias_detection.proxy.ProxyType | Not checked | Bias detection | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.bias_detection.proxy.ProxyVariableResult | Checked | Bias detection | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.proxy.ProxyVariableResult.to_dict | Not checked | Bias detection | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.bias_detection.proxy.compute_proxy_correlations | Not checked | Bias detection | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.bias_detection.proxy.find_proxy_chains | Checked | Bias detection | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.proxy.identify_proxy_variables | Checked | Bias detection | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.proxy.multivariate_proxy_leakage | Checked | Bias detection | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.bias_detection.representation.RepresentationBiasResult | Checked | Bias detection | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.representation.RepresentationBiasResult.to_dict | Not checked | Bias detection | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.bias_detection.representation.RepresentationSeverity | Not checked | Bias detection | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.bias_detection.representation.calculate_representation_ratio | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.representation.compare_to_benchmark | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.representation.detect_representation_bias | Checked | Bias detection | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.statistical.DisparityType | Not checked | Bias detection | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.bias_detection.statistical.EffectSizeInterpretation | Not checked | Bias detection | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.bias_detection.statistical.SignificanceLevel | Not checked | Bias detection | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.bias_detection.statistical.StatisticalDisparityResult | Checked | Bias detection | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.bias_detection.statistical.StatisticalDisparityResult.to_dict | Not checked | Bias detection | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.bias_detection.statistical.analyze_statistical_disparities | Checked | Bias detection | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.bias_detection.statistical.compute_effect_sizes | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.statistical.detect_specification_bias | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.statistical.detect_temporal_drift | Not checked | Bias detection | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.bias_detection.statistical.run_disparity_tests | Not checked | Bias detection | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.analyzer.FeatureAnalysisReport | Checked | Preprocessing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.analyzer.FeatureAnalysisReport.to_dict | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureAnalysisReport.to_json | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer | Checked | Preprocessing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.analyze_proxies | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.compare_transformations | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.full_analysis | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.get_correlation_matrix | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.get_explanation | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.get_feature_correlation_matrix | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.get_feature_recommendations | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.get_transformation_report | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.analyzer.FeatureEngineeringAnalyzer.transform | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.analyzer.ProxyScreenFindings | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.correlation.CorrelationResult | Checked | Preprocessing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.correlation.CorrelationResult.to_dict | Not checked | Preprocessing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.correlation.CorrelationType | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.correlation.FeatureCorrelationMatrix | Checked | Preprocessing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.correlation.FeatureCorrelationMatrix.get_high_correlations | Not checked | Preprocessing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.correlation.FeatureCorrelationMatrix.to_dict | Not checked | Preprocessing mitigation | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.feature_engineering.correlation.ProxyChainResult | Checked | Preprocessing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.correlation.ProxyChainResult.to_dict | Not checked | Preprocessing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.correlation.ProxyRiskLevel | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.correlation.ProxyScreenResult | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.correlation.ProxyType | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.correlation.ProxyVariableResult | Checked | Preprocessing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.correlation.ProxyVariableResult.to_dict | Not checked | Preprocessing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.correlation.analyze_intersectional_correlations | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.correlation.compute_feature_correlations | Checked | Preprocessing mitigation | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.correlation.compute_pearson_correlation_matrix | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.correlation.find_proxy_chains | Checked | Preprocessing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.correlation.identify_proxy_variables | Not checked | Preprocessing mitigation | function | executed, and on 1 world(s) where nothing was measurable (empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.preprocessing.feature_engineering.data_balancing.ADASYNResampler | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.data_balancing.CounterfactualAugmenter | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.data_balancing.CounterfactualAugmenter.fit | Not checked | Preprocessing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.data_balancing.CounterfactualAugmenter.get_resampled_data | Not checked | Preprocessing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.data_balancing.CounterfactualAugmenter.transform | Not checked | Preprocessing mitigation | method | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.data_balancing.InversePropensityWeighter | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.data_balancing.PropensityScoreWeighter | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.data_balancing.SMOTEResampler | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.data_balancing.SyntheticResampler | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.data_balancing.SyntheticResampler.fit | Not checked | Preprocessing mitigation | method | could not be called without a hand-built fixture |
vfairness.preprocessing.feature_engineering.data_balancing.SyntheticResampler.get_resampled_data | Not checked | Preprocessing mitigation | method | could not be called without a hand-built fixture |
vfairness.preprocessing.feature_engineering.data_balancing.SyntheticResampler.transform | Not checked | Preprocessing mitigation | method | could not be called without a hand-built fixture |
vfairness.preprocessing.feature_engineering.data_balancing.TomekResampler | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.data_balancing.counterfactual_augment | Checked | Preprocessing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.data_balancing.propensity_weights | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.significance.paired_metric_significance | Not checked | Preprocessing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.feature_engineering.transformers.BaseFeatureTransformer | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.transformers.BaseFeatureTransformer.fit | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.BaseFeatureTransformer.fit_transform | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.BaseFeatureTransformer.get_feature_names_out | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.BaseFeatureTransformer.transform | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.CorrelationReducer | Checked | Preprocessing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.transformers.CorrelationReducer.fit | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.CorrelationReducer.transform | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.DisparateImpactRemover | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.transformers.DisparateImpactRemover.fit | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.DisparateImpactRemover.transform | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.FairRepresentationTransformer | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.transformers.FairRepresentationTransformer.fit | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.FairRepresentationTransformer.transform | Checked | Preprocessing mitigation | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.transformers.FairnessObjective | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.transformers.FeatureImportanceResult | Checked | Preprocessing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.FeatureImportanceResult.to_dict | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.FeatureSuppressor | Checked | Preprocessing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.transformers.FeatureSuppressor.fit | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.FeatureSuppressor.transform | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.IntersectionalTransformer | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.transformers.IntersectionalTransformer.fit | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.transformers.IntersectionalTransformer.transform | Checked | Preprocessing mitigation | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.transformers.LabelMassager | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.transformers.LabelMassager.fit | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.LabelMassager.get_massaged_labels | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.LabelMassager.transform | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.Resampler | Checked | Preprocessing mitigation | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.transformers.Resampler.fit | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.Resampler.get_resampled_data | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.Resampler.transform | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.ResidualTransformer | Checked | Preprocessing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.transformers.ResidualTransformer.fit | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.ResidualTransformer.transform | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.ReweightingTransformer | Checked | Preprocessing mitigation | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.transformers.ReweightingTransformer.fit | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.ReweightingTransformer.get_sample_weights | Fix pending | Preprocessing mitigation | method | proved to report, or to claim, something nobody measured |
vfairness.preprocessing.feature_engineering.transformers.ReweightingTransformer.transform | Checked | Preprocessing mitigation | method | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.TransformationMethod | Not checked | Preprocessing mitigation | class | could not be constructed without a hand-built fixture |
vfairness.preprocessing.feature_engineering.transformers.TransformationResult | Checked | Preprocessing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.feature_engineering.transformers.TransformationResult.to_dict | Checked | Preprocessing mitigation | method | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.preprocessing.feature_engineering.visualization.create_analysis_dashboard | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.visualization.plot_correlation_bars | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.visualization.plot_correlation_heatmap | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.visualization.plot_feature_correlation_matrix | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.visualization.plot_feature_transformation_effect | Not checked | Preprocessing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.feature_engineering.visualization.plot_intersectional_heatmap | Checked | Preprocessing mitigation | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.preprocessing.feature_engineering.visualization.plot_proxy_chains | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.visualization.plot_proxy_risk_chart | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.visualization.plot_risk_distribution | Not checked | Preprocessing mitigation | function | called, but the call itself failed, so nothing was learned about it |
vfairness.preprocessing.feature_engineering.visualization.plot_transformation_comparison | Not checked | Preprocessing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preprocessing.protected_binning.PreparedProtected | Checked | Preprocessing mitigation | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.preprocessing.protected_binning.prepare_protected_attributes | Not checked | Preprocessing mitigation | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.preview_palette | Not checked | Top level | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters.bias_audit_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters.calibration_report_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters.cicd_pipeline_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters.fairness_report_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_calibration.calibration_disparity_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_calibration.group_calibration_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_calibration.pareto_frontier_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_calibration.reliability_diagram_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_discovery.auto_discovery_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_experimentation.causal_decomposition_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_experimentation.experiment_recommendation_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_experimentation.experiment_results_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_experimentation.power_analysis_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_fairness.confidence_intervals_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_fairness.disparity_heatmap_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_fairness.effect_sizes_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_fairness.group_comparison_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_fairness.metrics_bar_chart_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_fairness.radar_chart_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_fairness.report_assessability | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_feature_engineering.correlation_heatmap_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_feature_engineering.correlation_matrix_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_feature_engineering.intersectional_analysis_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_feature_engineering.intersectional_disparity_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_feature_engineering.proxy_risk_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_feature_engineering.transformation_comparison_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_monitoring.alert_timeline_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_monitoring.drift_report_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_monitoring.monitoring_dashboard_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_monitoring.temporal_analysis_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_post_processing.fairness_detailed_report_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_post_processing.reweighting_comparison_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_post_processing.threshold_optimization_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_ranking.ranking_fairness_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_regression.regression_fairness_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_reporting.reporting_dashboard_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_robustness.robustness_testing_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_training.method_comparison_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_training.tradeoff_analysis_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_training.training_analysis_report_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_training.training_report_to_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.adapters_validation.data_validation_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_workflow.hierarchical_gate_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_workflow.report_card_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.adapters_workflow.workflow_overview_to_svg | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.engine.get_template_path | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.engine.list_templates | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.engine.raise_jinja2_missing | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.engine.render_svg | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.explain.ChartExplanation | Checked | Report rendering | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.rendering.explain.ChartExplanation.caption | Not checked | Report rendering | method | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.explain.ChartExplanation.metadata | Not checked | Report rendering | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.explain.ChartExplanation.paragraph | Not checked | Report rendering | method | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.explain.build_explanation | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.explain.inject_accessibility | Not checked | Report rendering | function | called, but the call itself failed, so nothing was learned about it |
vfairness.rendering.skins.apply_skin | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.rendering.skins.list_skins | Not checked | Report rendering | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.result.TaskResult | Checked | Top level | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.result.TaskResult.to_dict | Not checked | Top level | method | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.save_fairness_plots | Not checked | Top level | function | called, but the call itself failed, so nothing was learned about it |
vfairness.streaming.stream_group_counts | Not checked | Top level | function | executed, and on 2 world(s) where nothing was measurable (all_nan_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.streaming.streaming_demographic_parity | Not checked | Top level | function | executed, and on 2 world(s) where nothing was measurable (constant_scores, one_label_only) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.streaming.streaming_selection_rates | Not checked | Top level | function | executed, and on 2 world(s) where nothing was measurable (all_nan_scores, empty) it returned a neutral value and warned nobody. Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.validity.aggregate.aggregate_validity | Not checked | Validity axis | function | called, but the call itself failed, so nothing was learned about it |
vfairness.validity.groundedness.GoldUnsupportedWarning | Checked | Validity axis | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.validity.groundedness.GroundednessJudge | Not checked | Validity axis | class | could not be constructed without a hand-built fixture |
vfairness.validity.groundedness.GroundednessJudge.judge_groundedness | Not checked | Validity axis | method | could not be called without a hand-built fixture |
vfairness.validity.groundedness.GroundednessResult | Checked | Validity axis | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.validity.groundedness.GroundednessScorer | Checked | Validity axis | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.validity.groundedness.GroundednessScorer.score | Not checked | Validity axis | method | called, but the call itself failed, so nothing was learned about it |
vfairness.validity.groundedness.ValidityScorerUnavailableWarning | Checked | Validity axis | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.validity.groundedness.groundedness_scorer_status | Not checked | Validity axis | function | called, but the call itself failed, so nothing was learned about it |
vfairness.validity.judge.LlmGroundednessJudge | Not checked | Validity axis | class | could not be constructed without a hand-built fixture |
vfairness.validity.judge.LlmGroundednessJudge.judge_groundedness | Not checked | Validity axis | method | could not be called without a hand-built fixture |
vfairness.vision.NDKLValue | Not checked | Vision | class | could not be constructed without a hand-built fixture |
vfairness.vision.bias_amplification | Checked | Vision | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.vision.classify_face_demographics | Not checked | Vision | function | executed on healthy and degenerate input; the evidence has not been judged yet |
vfairness.vision.ndkl | Checked | Vision | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.vision.representation_severity | Checked | Vision | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.vision.skew | Checked | Vision | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.xai.decomposition.shap_fairness.lundberg_fairness_decomposition | Checked | Explainability (XAI) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.xai.decomposition.shap_fairness.proxy_score | Checked | Explainability (XAI) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.xai.diagnostics.adversarial.AdversarialProbeResult | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.diagnostics.adversarial.multi_seed_adversarial_probe | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: the healthy world did not produce a value (ValueError: shape mismatch: objects cannot be broadcast to a single shape. Mismatch is between arg 0 with shape (200, 120) and arg ) |
vfairness.xai.diagnostics.adversarial.slack_adversarial_probe | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: the healthy world did not produce a value (ValueError: shape mismatch: objects cannot be broadcast to a single shape. Mismatch is between arg 0 with shape (200, 120) and arg ) |
vfairness.xai.diagnostics.faithfulness.local_r_squared | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.diagnostics.faithfulness.removal_curve_auc | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: the healthy world did not produce a value (ValueError: X has 480 features, but LogisticRegression is expecting 4 features as input.) |
vfairness.xai.diagnostics.stability.attribution_stability | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.anchors_adapter.AnchorsExplainer | Checked | Explainability (XAI) | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.explainers.anchors_adapter.AnchorsExplainer.explain_global | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.anchors_adapter.AnchorsExplainer.explain_local | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (ValueError: X has 480 features, but LogisticRegression is expecting 4 features as input.) |
vfairness.xai.explainers.anchors_adapter.AnchorsExplainer.supports | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.base.Explainer | Not checked | Explainability (XAI) | class | could not be constructed without a hand-built fixture |
vfairness.xai.explainers.base.Explainer.explain_global | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.base.Explainer.explain_local | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.base.Explainer.supports | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.base.ExplainerCapabilities | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.explainers.dice_adapter.DiceCounterfactualExplainer | Checked | Explainability (XAI) | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.explainers.dice_adapter.DiceCounterfactualExplainer.explain_global | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.dice_adapter.DiceCounterfactualExplainer.explain_local | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (ValueError: DiceCounterfactualExplainer.explain_local requires `dataframe` (pandas, including the outcome column) and `outcome_name`) |
vfairness.xai.explainers.dice_adapter.DiceCounterfactualExplainer.supports | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.ig_adapter.IntegratedGradientsExplainer | Checked | Explainability (XAI) | class | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.xai.explainers.ig_adapter.IntegratedGradientsExplainer.explain_global | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (AttributeError: 'LogisticRegression' object has no attribute 'eval') |
vfairness.xai.explainers.ig_adapter.IntegratedGradientsExplainer.explain_local | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (AttributeError: 'LogisticRegression' object has no attribute 'eval') |
vfairness.xai.explainers.ig_adapter.IntegratedGradientsExplainer.supports | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.ig_adapter.completeness_scale | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.lime_adapter.LimeExplainer | Checked | Explainability (XAI) | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.explainers.lime_adapter.LimeExplainer.explain_global | Not checked | Explainability (XAI) | method | executed against a fitted model: answered without a warning on 2 world(s) where no attribution is defined (all_constant, empty). Suspected fabrication, not yet judged: treat its output as unverified. |
vfairness.xai.explainers.lime_adapter.LimeExplainer.explain_local | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (ValueError: X has 480 features, but LogisticRegression is expecting 4 features as input.) |
vfairness.xai.explainers.lime_adapter.LimeExplainer.supports | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.registry.available_methods | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.registry.get_explainer | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.router.RouteDecision | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.explainers.router.route_explainer | Checked | Explainability (XAI) | function | refuses honestly when nothing is measurable, and a test fails if that regresses |
vfairness.xai.explainers.shap_adapter.KernelShapExplainer | Checked | Explainability (XAI) | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.explainers.shap_adapter.KernelShapExplainer.explain_global | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (TypeError: 'LogisticRegression' object is not callable) |
vfairness.xai.explainers.shap_adapter.KernelShapExplainer.explain_local | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (TypeError: 'LogisticRegression' object is not callable) |
vfairness.xai.explainers.shap_adapter.KernelShapExplainer.supports | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.shap_adapter.LinearShapExplainer | Checked | Explainability (XAI) | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.explainers.shap_adapter.LinearShapExplainer.explain_global | Checked | Explainability (XAI) | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.explainers.shap_adapter.LinearShapExplainer.explain_local | Checked | Explainability (XAI) | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.explainers.shap_adapter.LinearShapExplainer.supports | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.explainers.shap_adapter.TreeShapExplainer | Checked | Explainability (XAI) | class | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.explainers.shap_adapter.TreeShapExplainer.explain_global | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (InvalidModelError: Model type not yet supported by TreeExplainer: <class 'sklearn.linear_model._logistic.LogisticRegression'>) |
vfairness.xai.explainers.shap_adapter.TreeShapExplainer.explain_local | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: the healthy world did not produce a value (InvalidModelError: Model type not yet supported by TreeExplainer: <class 'sklearn.linear_model._logistic.LogisticRegression'>) |
vfairness.xai.explainers.shap_adapter.TreeShapExplainer.supports | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.schemas.AdvisorAlternative | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.AdvisorWarning | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.Attribution | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.ConflictFlag | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.CounterfactualExplanation | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.CounterfactualExplanation.to_db_row | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.schemas.CounterfactualInstance | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.Explanation | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.Explanation.to_db_row | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.schemas.FairnessDecomposition | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.FairnessDecomposition.assert_identity | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.schemas.FairnessDecomposition.to_db_row | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.schemas.Recommendation | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.ReconciledFinding | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.TrustPosture | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.ViewSection | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.XaiAssessment | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.schemas.XaiDiagnostics | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.sidecar_cli.main | Checked | Explainability (XAI) | function | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.storage.audit_artifact.build_audit_artifact_bundle | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.storage.supabase_writer.SupabaseWriter | Not checked | Explainability (XAI) | class | could not be constructed without a hand-built fixture |
vfairness.xai.storage.supabase_writer.SupabaseWriter.update_job_progress | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.storage.supabase_writer.SupabaseWriter.write_assessment | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.storage.supabase_writer.SupabaseWriter.write_audit_artifact | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.storage.supabase_writer.SupabaseWriter.write_explanations | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.storage.supabase_writer.SupabaseWriter.write_fairness_decomposition | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.storage.supabase_writer.SupabaseWriterError | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.worker.runner.WorkerConfig | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.worker.runner.WorkerLoop | Checked | Explainability (XAI) | class | returns no fairness number and no verdict, so it cannot fabricate one |
vfairness.xai.worker.runner.WorkerLoop.run | Not checked | Explainability (XAI) | method | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |
vfairness.xai.worker.runner.WorkerLoop.stop | Checked | Explainability (XAI) | method | verified by running it; no test pins the behaviour, so a regression would be silent |
vfairness.xai.worker.runner.main | Not checked | Explainability (XAI) | function | the explainability probe could not reach it: it takes none of the data these worlds vary (no x, X or attributions parameter), so nothing they do says anything about it |