{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YUEHXSRF3K6GFX6G3TSK4THAPN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a0eb4ff2726f94dd6c10181f92c9044468c2d6ca368c9edadfea4d8331ebdf04","cross_cats_sorted":["cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-13T15:42:31Z","title_canon_sha256":"e4a3222f790d55aa531fb1adf5a4519182e62c1c9d05efe3a45e10f23a15038f"},"schema_version":"1.0","source":{"id":"2603.13452","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.13452","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"arxiv_version","alias_value":"2603.13452v3","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.13452","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"pith_short_12","alias_value":"YUEHXSRF3K6G","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"pith_short_16","alias_value":"YUEHXSRF3K6GFX6G","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"pith_short_8","alias_value":"YUEHXSRF","created_at":"2026-05-20T00:01:40Z"}],"graph_snapshots":[{"event_id":"sha256:32acffba6911a38466008146d8b2eeceaff3f1ddb65a674b255a60d1e967d63a","target":"graph","created_at":"2026-05-20T00:01:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MESD reveals procedural disparities invisible to outcome metrics alone."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That disparities in explanation quality across intersectional subgroups, as measured by stability, directly indicate violations of procedural fairness principles."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MESD is a new procedural fairness metric that quantifies disparities in explanation quality across intersectional subgroups by combining label-aware aggregation, empirical-Bayes shrinkage, and CVaR weighting."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MESD quantifies disparities in explanation stability across intersectional subgroups to detect procedural unfairness missed by outcome metrics."}],"snapshot_sha256":"69154e0db52c4a90c6704d89fe6d552a1425b84d0074400e1442d1b090bd75dc"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bd6e987b006378129cb816bf9744d9e11a649afda373a4ce810b0139970bcf7c"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.13452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fairness in machine learning is predominantly evaluated through outcome-oriented metrics, such as Demographic parity, which measure whether predictions are statistically consistent across protected groups. However, these metrics cannot detect whether a model uses systematically different reasoning for different demographic groups, which violates procedural fairness principles. This problem is compounded by intersectionality, where models may appear fair on individual attributes (e.g., race) while exhibiting significant disparities for intersectional subgroups (e.g., race $\\times$ gender), a ph","authors_text":"Gideon Popoola, John Sheppard","cross_cats":["cs.CY","cs.LG"],"headline":"MESD quantifies disparities in explanation stability across intersectional subgroups to detect procedural unfairness missed by outcome metrics.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-13T15:42:31Z","title":"MESD: A Risk-Sensitive Metric for Explanation Fairness Across Intersectional Subgroups"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.13452","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T11:49:30.289865Z","id":"ea6fd4f7-1408-41d1-b7ae-8842d39220fa","model_set":{"reader":"grok-4.3"},"one_line_summary":"MESD is a new procedural fairness metric that quantifies disparities in explanation quality across intersectional subgroups by combining label-aware aggregation, empirical-Bayes shrinkage, and CVaR weighting.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MESD quantifies disparities in explanation stability across intersectional subgroups to detect procedural unfairness missed by outcome metrics.","strongest_claim":"MESD reveals procedural disparities invisible to outcome metrics alone.","weakest_assumption":"That disparities in explanation quality across intersectional subgroups, as measured by stability, directly indicate violations of procedural fairness principles."}},"verdict_id":"ea6fd4f7-1408-41d1-b7ae-8842d39220fa"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:59434cb9f9d4b24a78ad895d2fdf93dfbfcbda1856613e6f1a98c76d0a676d45","target":"record","created_at":"2026-05-20T00:01:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a0eb4ff2726f94dd6c10181f92c9044468c2d6ca368c9edadfea4d8331ebdf04","cross_cats_sorted":["cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-13T15:42:31Z","title_canon_sha256":"e4a3222f790d55aa531fb1adf5a4519182e62c1c9d05efe3a45e10f23a15038f"},"schema_version":"1.0","source":{"id":"2603.13452","kind":"arxiv","version":3}},"canonical_sha256":"c5087bca25dabc62dfc6dce4ae4ce07b5c25c6e082bc65a9b2c429ac3556923f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5087bca25dabc62dfc6dce4ae4ce07b5c25c6e082bc65a9b2c429ac3556923f","first_computed_at":"2026-05-20T00:01:40.162138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:40.162138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZEuuToHhTe90vHQQ9JJh2Jiou5Q470OEpSGY+oUa9sFIFvV6zlfgrsTYiwIoWR/e6sYEjbc4UouMCNW4yrMhBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:40.162912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.13452","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59434cb9f9d4b24a78ad895d2fdf93dfbfcbda1856613e6f1a98c76d0a676d45","sha256:32acffba6911a38466008146d8b2eeceaff3f1ddb65a674b255a60d1e967d63a"],"state_sha256":"f4859ce285c3796f77250ff92f239a56ff11dd9f951ac3e75906d0031c1453e0"}