{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EDAYGOYNMOW777Z2DHA3CLJSI6","short_pith_number":"pith:EDAYGOYN","schema_version":"1.0","canonical_sha256":"20c1833b0d63adffff3a19c1b12d3247baf32d2c18f74391c235155af2e012a6","source":{"kind":"arxiv","id":"2401.14893","version":2},"attestation_state":"computed","paper":{"title":"A structured regression approach for evaluating model performance across intersectional subgroups","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandra Chouldechova, Christine Herlihy, Kimberly Truong, Miroslav Dudik","submitted_at":"2024-01-26T14:21:45Z","abstract_excerpt":"Disaggregated evaluation is a central task in AI fairness assessment, where the goal is to measure an AI system's performance across different subgroups defined by combinations of demographic or other sensitive attributes. The standard approach is to stratify the evaluation data across subgroups and compute performance metrics separately for each group. However, even for moderately-sized evaluation datasets, sample sizes quickly get small once considering intersectional subgroups, which greatly limits the extent to which intersectional groups are included in analysis. In this work, we introduc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.14893","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T14:21:45Z","cross_cats_sorted":["cs.CY","stat.AP","stat.ML"],"title_canon_sha256":"db96abade1748a339a68fdc326858ccdbf8dc368f21e0a059fa35b990d91c0de","abstract_canon_sha256":"74bf6bcbc4922fa029bfcbff9c5bab37fcf59fef6e8315ef0cebac4a8fd0f910"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:48.567498Z","signature_b64":"oiBdCn+m/I8ONbCMhXx5Umr3GscB771zIcvH356nluKIFSvRKruAHelNf7wFe0wageEWFEcWy8LW3LRHDSZBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20c1833b0d63adffff3a19c1b12d3247baf32d2c18f74391c235155af2e012a6","last_reissued_at":"2026-07-05T08:18:48.566973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:48.566973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A structured regression approach for evaluating model performance across intersectional subgroups","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandra Chouldechova, Christine Herlihy, Kimberly Truong, Miroslav Dudik","submitted_at":"2024-01-26T14:21:45Z","abstract_excerpt":"Disaggregated evaluation is a central task in AI fairness assessment, where the goal is to measure an AI system's performance across different subgroups defined by combinations of demographic or other sensitive attributes. The standard approach is to stratify the evaluation data across subgroups and compute performance metrics separately for each group. However, even for moderately-sized evaluation datasets, sample sizes quickly get small once considering intersectional subgroups, which greatly limits the extent to which intersectional groups are included in analysis. In this work, we introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14893","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.14893/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.14893","created_at":"2026-07-05T08:18:48.567030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14893v2","created_at":"2026-07-05T08:18:48.567030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14893","created_at":"2026-07-05T08:18:48.567030+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDAYGOYNMOW7","created_at":"2026-07-05T08:18:48.567030+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDAYGOYNMOW777Z2","created_at":"2026-07-05T08:18:48.567030+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDAYGOYN","created_at":"2026-07-05T08:18:48.567030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19357","citing_title":"FairTree: Subgroup Fairness Auditing of Machine Learning Models with Bias-Variance Decomposition","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6","json":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6.json","graph_json":"https://pith.science/api/pith-number/EDAYGOYNMOW777Z2DHA3CLJSI6/graph.json","events_json":"https://pith.science/api/pith-number/EDAYGOYNMOW777Z2DHA3CLJSI6/events.json","paper":"https://pith.science/paper/EDAYGOYN"},"agent_actions":{"view_html":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6","download_json":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6.json","view_paper":"https://pith.science/paper/EDAYGOYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14893&json=true","fetch_graph":"https://pith.science/api/pith-number/EDAYGOYNMOW777Z2DHA3CLJSI6/graph.json","fetch_events":"https://pith.science/api/pith-number/EDAYGOYNMOW777Z2DHA3CLJSI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6/action/storage_attestation","attest_author":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6/action/author_attestation","sign_citation":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6/action/citation_signature","submit_replication":"https://pith.science/pith/EDAYGOYNMOW777Z2DHA3CLJSI6/action/replication_record"}},"created_at":"2026-07-05T08:18:48.567030+00:00","updated_at":"2026-07-05T08:18:48.567030+00:00"}