{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NQP4PCRTIKCJ7QYEIW2VRKHW5T","short_pith_number":"pith:NQP4PCRT","schema_version":"1.0","canonical_sha256":"6c1fc78a3342849fc30445b558a8f6ecf09f79e309a81d4ec7fe1226f390d96d","source":{"kind":"arxiv","id":"2505.17533","version":1},"attestation_state":"computed","paper":{"title":"Learning Representational Disparities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Daniel B. Neill, Pavan Ravishankar, Rushabh Shah","submitted_at":"2025-05-23T06:40:24Z","abstract_excerpt":"We propose a fair machine learning algorithm to model interpretable differences between observed and desired human decision-making, with the latter aimed at reducing disparity in a downstream outcome impacted by the human decision. Prior work learns fair representations without considering the outcome in the decision-making process. We model the outcome disparities as arising due to the different representations of the input seen by the observed and desired decision-maker, which we term representational disparities. Our goal is to learn interpretable representational disparities which could po"},"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":"2505.17533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T06:40:24Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"9bf3a17e9153bb73aedbe11ce137bc42828570e4b05fc0a001cc282981c8f279","abstract_canon_sha256":"325a9f40375f72556e9e3f98051360132fd88eb71043d76c55ee7b866f3fabaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:27.772451Z","signature_b64":"rYLB+dzd+ez9AAngBtKHNpMXJgv/du1RWhDSqS0VUAie2l2h2MUFnR19SKf9QoJv1K/hWULHeuidmPCxFqE1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c1fc78a3342849fc30445b558a8f6ecf09f79e309a81d4ec7fe1226f390d96d","last_reissued_at":"2026-07-05T11:08:27.771972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:27.771972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Representational Disparities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Daniel B. Neill, Pavan Ravishankar, Rushabh Shah","submitted_at":"2025-05-23T06:40:24Z","abstract_excerpt":"We propose a fair machine learning algorithm to model interpretable differences between observed and desired human decision-making, with the latter aimed at reducing disparity in a downstream outcome impacted by the human decision. Prior work learns fair representations without considering the outcome in the decision-making process. We model the outcome disparities as arising due to the different representations of the input seen by the observed and desired decision-maker, which we term representational disparities. Our goal is to learn interpretable representational disparities which could po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17533","kind":"arxiv","version":1},"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/2505.17533/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":"2505.17533","created_at":"2026-07-05T11:08:27.772029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17533v1","created_at":"2026-07-05T11:08:27.772029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17533","created_at":"2026-07-05T11:08:27.772029+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQP4PCRTIKCJ","created_at":"2026-07-05T11:08:27.772029+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQP4PCRTIKCJ7QYE","created_at":"2026-07-05T11:08:27.772029+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQP4PCRT","created_at":"2026-07-05T11:08:27.772029+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/NQP4PCRTIKCJ7QYEIW2VRKHW5T","json":"https://pith.science/pith/NQP4PCRTIKCJ7QYEIW2VRKHW5T.json","graph_json":"https://pith.science/api/pith-number/NQP4PCRTIKCJ7QYEIW2VRKHW5T/graph.json","events_json":"https://pith.science/api/pith-number/NQP4PCRTIKCJ7QYEIW2VRKHW5T/events.json","paper":"https://pith.science/paper/NQP4PCRT"},"agent_actions":{"view_html":"https://pith.science/pith/NQP4PCRTIKCJ7QYEIW2VRKHW5T","download_json":"https://pith.science/pith/NQP4PCRTIKCJ7QYEIW2VRKHW5T.json","view_paper":"https://pith.science/paper/NQP4PCRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17533&json=true","fetch_graph":"https://pith.science/api/pith-number/NQP4PCRTIKCJ7QYEIW2VRKHW5T/graph.json","fetch_events":"https://pith.science/api/pith-number/NQP4PCRTIKCJ7QYEIW2VRKHW5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQP4PCRTIKCJ7QYEIW2VRKHW5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQP4PCRTIKCJ7QYEIW2VRKHW5T/action/storage_attestation","attest_author":"https://pith.science/pith/NQP4PCRTIKCJ7QYEIW2VRKHW5T/action/author_attestation","sign_citation":"https://pith.science/pith/NQP4PCRTIKCJ7QYEIW2VRKHW5T/action/citation_signature","submit_replication":"https://pith.science/pith/NQP4PCRTIKCJ7QYEIW2VRKHW5T/action/replication_record"}},"created_at":"2026-07-05T11:08:27.772029+00:00","updated_at":"2026-07-05T11:08:27.772029+00:00"}