{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:NAWHNCBNLL6HD5AL3A7BVXIZNZ","short_pith_number":"pith:NAWHNCBN","schema_version":"1.0","canonical_sha256":"682c76882d5afc71f40bd83e1add196e712673f556a2d2d1c8dfe06ceb2e93e2","source":{"kind":"arxiv","id":"1412.3756","version":3},"attestation_state":"computed","paper":{"title":"Certifying and removing disparate impact","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"stat.ML","authors_text":"Carlos Scheidegger, John Moeller, Michael Feldman, Sorelle Friedler, Suresh Venkatasubramanian","submitted_at":"2014-12-11T18:42:59Z","abstract_excerpt":"What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender, religious practice) and an explicit description of the process.\n  When the process is implemented using computers, determining disparate impact (and hence bias) is harder. It might not be possible to disclose the process. In addition, even if the process is open, it might "},"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":"1412.3756","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-11T18:42:59Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"c401f089531c4aad052fd20c08f1bc6c378bb2bdab17de923c488669acf331bd","abstract_canon_sha256":"d694bc66ddc84906ebee894a0cf9ff9805585b5140b67f84902e4da72995e909"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:48.144394Z","signature_b64":"WPZ7z1GxmKGOCHMNxQhfwk4tLswU35lxXs/YLp1XwTp6ZWsW3GB3TMhvhYVhi12PZELSrkB78CQ4A6ulBRNGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"682c76882d5afc71f40bd83e1add196e712673f556a2d2d1c8dfe06ceb2e93e2","last_reissued_at":"2026-05-18T01:36:48.143718Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:48.143718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certifying and removing disparate impact","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"stat.ML","authors_text":"Carlos Scheidegger, John Moeller, Michael Feldman, Sorelle Friedler, Suresh Venkatasubramanian","submitted_at":"2014-12-11T18:42:59Z","abstract_excerpt":"What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender, religious practice) and an explicit description of the process.\n  When the process is implemented using computers, determining disparate impact (and hence bias) is harder. It might not be possible to disclose the process. In addition, even if the process is open, it might "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.3756","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1412.3756","created_at":"2026-05-18T01:36:48.143808+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.3756v3","created_at":"2026-05-18T01:36:48.143808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.3756","created_at":"2026-05-18T01:36:48.143808+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAWHNCBNLL6H","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAWHNCBNLL6HD5AL","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAWHNCBN","created_at":"2026-05-18T12:28:41.024544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.20220","citing_title":"Alternatives to the Laplacian for Scalable Spectral Clustering with Group Fairness Constraints","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23786","citing_title":"FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ","json":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ.json","graph_json":"https://pith.science/api/pith-number/NAWHNCBNLL6HD5AL3A7BVXIZNZ/graph.json","events_json":"https://pith.science/api/pith-number/NAWHNCBNLL6HD5AL3A7BVXIZNZ/events.json","paper":"https://pith.science/paper/NAWHNCBN"},"agent_actions":{"view_html":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ","download_json":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ.json","view_paper":"https://pith.science/paper/NAWHNCBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.3756&json=true","fetch_graph":"https://pith.science/api/pith-number/NAWHNCBNLL6HD5AL3A7BVXIZNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NAWHNCBNLL6HD5AL3A7BVXIZNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ/action/storage_attestation","attest_author":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ/action/author_attestation","sign_citation":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ/action/citation_signature","submit_replication":"https://pith.science/pith/NAWHNCBNLL6HD5AL3A7BVXIZNZ/action/replication_record"}},"created_at":"2026-05-18T01:36:48.143808+00:00","updated_at":"2026-05-18T01:36:48.143808+00:00"}