{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OKMTJRGFJ3DFEJELNJ76AE4JS7","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":"b49f722b1fb25b77c7806681ec1c42166b2c3cef5e48fc58f42eb2bae1ed4243","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T18:10:57Z","title_canon_sha256":"1f1f6439c864d6f2b289b47a2f866d75f99525d8e6587ee899bb6087e4be5dfc"},"schema_version":"1.0","source":{"id":"2605.15295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15295","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15295v1","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15295","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"OKMTJRGFJ3DF","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"OKMTJRGFJ3DFEJEL","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"OKMTJRGF","created_at":"2026-05-20T00:00:51Z"}],"graph_snapshots":[{"event_id":"sha256:dae1e07f5c2ecc315c2d05a7f4dfe2b9f8ad75d16f1e669a5f990650ccac44c8","target":"graph","created_at":"2026-05-20T00:00:51Z","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":"GESD effectively captures group-wise discrepancies in explanation quality, and that FEU improves both utility and fairness over state-of-the-art methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That measuring disparities in explanation stability, robustness, and sensitivity across subgroups provides a meaningful and model-agnostic indicator of procedural fairness without requiring additional assumptions about the underlying explainer or data distribution."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The paper proposes GESD, a procedural fairness metric for group disparities in explanation stability and robustness, and integrates it into the FEU multi-objective optimization framework."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GESD measures fairness by tracking how consistently machine learning models explain their predictions across demographic subgroups."}],"snapshot_sha256":"1ca1dc8307a2f54bc4e5b4dab6073b2f5d260198e71334d69e3ef06f5cdd119b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:36:04.312407Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.364619Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:41:54.234657Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.783854Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15295/integrity.json","findings":[],"snapshot_sha256":"a98ec30a092bbb9db1e30665e9f52baf73556af5ee2dcf02d682746a59cbc5fc","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning (ML) algorithms are increasingly deployed in high-stakes decision-making domains such as loan approvals, hiring, and recidivism predictions. While existing fairness metrics (e.g., statistical parity, equal opportunity) effectively quantify outcome-oriented disparities, they offer limited insight into the procedure or explanation behind biased decisions. To address this gap, we propose Group-level Explanation Stability Disparity (GESD), a \\textit{procedural-oriented} fairness metric that measures disparities in the stability, robustness, and sensitivity of model explanations ac","authors_text":"Gideon Popoola, John Sheppard","cross_cats":["cs.AI","cs.CY"],"headline":"GESD measures fairness by tracking how consistently machine learning models explain their predictions across demographic subgroups.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T18:10:57Z","title":"GESD: Beyond Outcome-Oriented Fairness"},"references":{"count":29,"internal_anchors":1,"resolved_work":29,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Big data’s disparate impact,","work_id":"8ef3fb2b-65b4-43d7-8193-87036d2fa1ed","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Investigating and mitigating the performance–fairness tradeoff via protected-category sampling,","work_id":"f9665236-7427-4074-b52c-1cdb2354e670","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Optimized pre-processing for discrimination prevention","work_id":"d285c33d-8270-4df5-a8ee-82dc61103423","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Fair prediction with disparate impact: A study of bias in recidivism prediction instruments,","work_id":"7a40f3a2-2b53-4d63-bed0-b01fd10cf685","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Equality of opportunity in super- vised learning,","work_id":"333f5ab2-14d7-4d29-a133-71e893194478","year":2016}],"snapshot_sha256":"c2753c2a08086e38f4cb6240f458c30266967cba1eb89159d91fdb882f4493f3"},"source":{"id":"2605.15295","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T16:26:09.804352Z","id":"0cd32de7-fc37-47ae-8460-3f4d0d03193e","model_set":{"reader":"grok-4.3"},"one_line_summary":"The paper proposes GESD, a procedural fairness metric for group disparities in explanation stability and robustness, and integrates it into the FEU multi-objective optimization framework.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GESD measures fairness by tracking how consistently machine learning models explain their predictions across demographic subgroups.","strongest_claim":"GESD effectively captures group-wise discrepancies in explanation quality, and that FEU improves both utility and fairness over state-of-the-art methods.","weakest_assumption":"That measuring disparities in explanation stability, robustness, and sensitivity across subgroups provides a meaningful and model-agnostic indicator of procedural fairness without requiring additional assumptions about the underlying explainer or data distribution."}},"verdict_id":"0cd32de7-fc37-47ae-8460-3f4d0d03193e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b7067baaa14cb521d1c019aa1b5c896d52a112598436414b454b679cd3960dad","target":"record","created_at":"2026-05-20T00:00:51Z","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":"b49f722b1fb25b77c7806681ec1c42166b2c3cef5e48fc58f42eb2bae1ed4243","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T18:10:57Z","title_canon_sha256":"1f1f6439c864d6f2b289b47a2f866d75f99525d8e6587ee899bb6087e4be5dfc"},"schema_version":"1.0","source":{"id":"2605.15295","kind":"arxiv","version":1}},"canonical_sha256":"729934c4c54ec652248b6a7fe0138997c749ff1a17cc3258d31df343839c6d20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"729934c4c54ec652248b6a7fe0138997c749ff1a17cc3258d31df343839c6d20","first_computed_at":"2026-05-20T00:00:51.173372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:51.173372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1chqexNJFE03nzParwBBEriAnOVNbfEgjIhb30Ct3rboHc2FoNhd7iJSrU3tAoZWI9iCr8KH9RxxbA9i3uV9CA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:51.174110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7067baaa14cb521d1c019aa1b5c896d52a112598436414b454b679cd3960dad","sha256:dae1e07f5c2ecc315c2d05a7f4dfe2b9f8ad75d16f1e669a5f990650ccac44c8"],"state_sha256":"0b4ba81846aab2693819f9c6f1343349634b45084735a42afa6ce846128ba74e"}