{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ADFQDRAKD2POEBZBTXIR53RBHS","short_pith_number":"pith:ADFQDRAK","schema_version":"1.0","canonical_sha256":"00cb01c40a1e9ee207219dd11eee213c99b1dc963322852abc209cf56a847ba4","source":{"kind":"arxiv","id":"1902.08283","version":5},"attestation_state":"computed","paper":{"title":"Capuchin: Causal Database Repair for Algorithmic Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Babak Salimi, Bill Howe, Dan Suciu, Luke Rodriguez","submitted_at":"2019-02-21T22:13:29Z","abstract_excerpt":"Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repair problem. Existing treatments of fairness rely on statistical correlations that can be fooled by statistical anomalies, such as Simpson's paradox. Proposals for causality-based definitions of fairness can correctly model some of these situations, but they require specification of the underlying causal models. In this paper, we formalize the situation as a database repair prob"},"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":"1902.08283","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-02-21T22:13:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"561ea007dd9756c399c8036648048fe5c012be901becbf0c6eb03307abe8fdf5","abstract_canon_sha256":"0edf513f0f6ac704f9eec1d8bb3640237233a86ffa15581b2ba24a4167929e52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:09:24.914876Z","signature_b64":"8+49lfG/BBQ2eyNjQ02pWO3MsWxOw+WZKX9XKPqM0e2u4DRzUeC+CQnT5ZtfWgnURQ1BUdlmrcn3U8IgjX18Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00cb01c40a1e9ee207219dd11eee213c99b1dc963322852abc209cf56a847ba4","last_reissued_at":"2026-07-05T00:09:24.914462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:09:24.914462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capuchin: Causal Database Repair for Algorithmic Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Babak Salimi, Bill Howe, Dan Suciu, Luke Rodriguez","submitted_at":"2019-02-21T22:13:29Z","abstract_excerpt":"Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repair problem. Existing treatments of fairness rely on statistical correlations that can be fooled by statistical anomalies, such as Simpson's paradox. Proposals for causality-based definitions of fairness can correctly model some of these situations, but they require specification of the underlying causal models. In this paper, we formalize the situation as a database repair prob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08283","kind":"arxiv","version":5},"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/1902.08283/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":"1902.08283","created_at":"2026-07-05T00:09:24.914520+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.08283v5","created_at":"2026-07-05T00:09:24.914520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08283","created_at":"2026-07-05T00:09:24.914520+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADFQDRAKD2PO","created_at":"2026-07-05T00:09:24.914520+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADFQDRAKD2POEBZB","created_at":"2026-07-05T00:09:24.914520+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADFQDRAK","created_at":"2026-07-05T00:09:24.914520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06443","citing_title":"The Fair Game: Auditing & Debiasing AI Algorithms Over Time","ref_index":111,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS","json":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS.json","graph_json":"https://pith.science/api/pith-number/ADFQDRAKD2POEBZBTXIR53RBHS/graph.json","events_json":"https://pith.science/api/pith-number/ADFQDRAKD2POEBZBTXIR53RBHS/events.json","paper":"https://pith.science/paper/ADFQDRAK"},"agent_actions":{"view_html":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS","download_json":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS.json","view_paper":"https://pith.science/paper/ADFQDRAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.08283&json=true","fetch_graph":"https://pith.science/api/pith-number/ADFQDRAKD2POEBZBTXIR53RBHS/graph.json","fetch_events":"https://pith.science/api/pith-number/ADFQDRAKD2POEBZBTXIR53RBHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS/action/storage_attestation","attest_author":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS/action/author_attestation","sign_citation":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS/action/citation_signature","submit_replication":"https://pith.science/pith/ADFQDRAKD2POEBZBTXIR53RBHS/action/replication_record"}},"created_at":"2026-07-05T00:09:24.914520+00:00","updated_at":"2026-07-05T00:09:24.914520+00:00"}