{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CQWGQCTTTBHNB4PPRT5IX3EQNL","short_pith_number":"pith:CQWGQCTT","schema_version":"1.0","canonical_sha256":"142c680a73984ed0f1ef8cfa8bec906aff39f0c18f882d26e26c8b591e8a46e8","source":{"kind":"arxiv","id":"2210.12546","version":1},"attestation_state":"computed","paper":{"title":"Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Eric Yang Yu, Min Kyung Lee, Sicun Gao, Zhizhen Qin","submitted_at":"2022-10-22T20:41:36Z","abstract_excerpt":"Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems in high-stake decision-making contexts. Recent work has proposed the use of Markov Decision Processes (MDPs) to formulate decision-making with long-term fairness requirements in dynamically changing environments, and demonstrated major challenges in directly deploying heuristic and rule-based policies that worked well in static environments. We show that policy optimization methods from deep reinforcement learning can be used to find strictly better decision policies that can o"},"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":"2210.12546","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T20:41:36Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"7266f1f56295fa8640cb5b60320049e72631b1dcfbddcf283cf4d5ab3448b712","abstract_canon_sha256":"665f1e471be3b2f4571ee8171aa27f24eb529c43ed7df472d6bc5e73d8940b76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:29.632331Z","signature_b64":"uUAu3rgvud80oJVmHMCW5omFNpwBer1vzRfJV41IczPtMYeIx00IB0MiSrAvKdf9FecOErf685wdU/ST1auUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142c680a73984ed0f1ef8cfa8bec906aff39f0c18f882d26e26c8b591e8a46e8","last_reissued_at":"2026-07-05T05:09:29.631949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:29.631949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Eric Yang Yu, Min Kyung Lee, Sicun Gao, Zhizhen Qin","submitted_at":"2022-10-22T20:41:36Z","abstract_excerpt":"Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems in high-stake decision-making contexts. Recent work has proposed the use of Markov Decision Processes (MDPs) to formulate decision-making with long-term fairness requirements in dynamically changing environments, and demonstrated major challenges in directly deploying heuristic and rule-based policies that worked well in static environments. We show that policy optimization methods from deep reinforcement learning can be used to find strictly better decision policies that can o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12546","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/2210.12546/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":"2210.12546","created_at":"2026-07-05T05:09:29.632015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12546v1","created_at":"2026-07-05T05:09:29.632015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12546","created_at":"2026-07-05T05:09:29.632015+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQWGQCTTTBHN","created_at":"2026-07-05T05:09:29.632015+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQWGQCTTTBHNB4PP","created_at":"2026-07-05T05:09:29.632015+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQWGQCTT","created_at":"2026-07-05T05:09:29.632015+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/CQWGQCTTTBHNB4PPRT5IX3EQNL","json":"https://pith.science/pith/CQWGQCTTTBHNB4PPRT5IX3EQNL.json","graph_json":"https://pith.science/api/pith-number/CQWGQCTTTBHNB4PPRT5IX3EQNL/graph.json","events_json":"https://pith.science/api/pith-number/CQWGQCTTTBHNB4PPRT5IX3EQNL/events.json","paper":"https://pith.science/paper/CQWGQCTT"},"agent_actions":{"view_html":"https://pith.science/pith/CQWGQCTTTBHNB4PPRT5IX3EQNL","download_json":"https://pith.science/pith/CQWGQCTTTBHNB4PPRT5IX3EQNL.json","view_paper":"https://pith.science/paper/CQWGQCTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12546&json=true","fetch_graph":"https://pith.science/api/pith-number/CQWGQCTTTBHNB4PPRT5IX3EQNL/graph.json","fetch_events":"https://pith.science/api/pith-number/CQWGQCTTTBHNB4PPRT5IX3EQNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQWGQCTTTBHNB4PPRT5IX3EQNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQWGQCTTTBHNB4PPRT5IX3EQNL/action/storage_attestation","attest_author":"https://pith.science/pith/CQWGQCTTTBHNB4PPRT5IX3EQNL/action/author_attestation","sign_citation":"https://pith.science/pith/CQWGQCTTTBHNB4PPRT5IX3EQNL/action/citation_signature","submit_replication":"https://pith.science/pith/CQWGQCTTTBHNB4PPRT5IX3EQNL/action/replication_record"}},"created_at":"2026-07-05T05:09:29.632015+00:00","updated_at":"2026-07-05T05:09:29.632015+00:00"}