{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TQD5EMTTMQKMWYT75WC52AOVZ4","short_pith_number":"pith:TQD5EMTT","schema_version":"1.0","canonical_sha256":"9c07d232736414cb627fed85dd01d5cf17c7e5c9ee77a229175363882c326e6f","source":{"kind":"arxiv","id":"1811.04973","version":2},"attestation_state":"computed","paper":{"title":"Eliminating Latent Discrimination: Train Then Mask","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amin Karbasi, Ehsan Kazemi, Soheil Ghili","submitted_at":"2018-11-12T19:25:05Z","abstract_excerpt":"How can we control for latent discrimination in predictive models? How can we provably remove it? Such questions are at the heart of algorithmic fairness and its impacts on society. In this paper, we define a new operational fairness criteria, inspired by the well-understood notion of omitted variable-bias in statistics and econometrics. Our notion of fairness effectively controls for sensitive features and provides diagnostics for deviations from fair decision making. We then establish analytical and algorithmic results about the existence of a fair classifier in the context of supervised lea"},"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":"1811.04973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-12T19:25:05Z","cross_cats_sorted":["cs.CY","stat.ML"],"title_canon_sha256":"f93bb80fe3374f4a1b646e050a8516085e5c324f713364f7e60127b32404638d","abstract_canon_sha256":"6d813fc37f81b08efd433f47a67f63f0c4d7a76ac187537cbfef7432eca271d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:58.567299Z","signature_b64":"QQ48NkarudeRHzEmdCt+5e62fARM5K58kTS2nmhLy609sosiaLLmRrbpZF9kqY6FhZkrWRtlbRa6pRxnjKMRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c07d232736414cb627fed85dd01d5cf17c7e5c9ee77a229175363882c326e6f","last_reissued_at":"2026-05-17T23:52:58.566599Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:58.566599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eliminating Latent Discrimination: Train Then Mask","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amin Karbasi, Ehsan Kazemi, Soheil Ghili","submitted_at":"2018-11-12T19:25:05Z","abstract_excerpt":"How can we control for latent discrimination in predictive models? How can we provably remove it? Such questions are at the heart of algorithmic fairness and its impacts on society. In this paper, we define a new operational fairness criteria, inspired by the well-understood notion of omitted variable-bias in statistics and econometrics. Our notion of fairness effectively controls for sensitive features and provides diagnostics for deviations from fair decision making. We then establish analytical and algorithmic results about the existence of a fair classifier in the context of supervised lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04973","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":""},"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":"1811.04973","created_at":"2026-05-17T23:52:58.566733+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.04973v2","created_at":"2026-05-17T23:52:58.566733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04973","created_at":"2026-05-17T23:52:58.566733+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQD5EMTTMQKM","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQD5EMTTMQKMWYT7","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQD5EMTT","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4","json":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4.json","graph_json":"https://pith.science/api/pith-number/TQD5EMTTMQKMWYT75WC52AOVZ4/graph.json","events_json":"https://pith.science/api/pith-number/TQD5EMTTMQKMWYT75WC52AOVZ4/events.json","paper":"https://pith.science/paper/TQD5EMTT"},"agent_actions":{"view_html":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4","download_json":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4.json","view_paper":"https://pith.science/paper/TQD5EMTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.04973&json=true","fetch_graph":"https://pith.science/api/pith-number/TQD5EMTTMQKMWYT75WC52AOVZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/TQD5EMTTMQKMWYT75WC52AOVZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4/action/storage_attestation","attest_author":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4/action/author_attestation","sign_citation":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4/action/citation_signature","submit_replication":"https://pith.science/pith/TQD5EMTTMQKMWYT75WC52AOVZ4/action/replication_record"}},"created_at":"2026-05-17T23:52:58.566733+00:00","updated_at":"2026-05-17T23:52:58.566733+00:00"}