{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PLMRJUC5RT5Z24GDWJ7YYDBBI5","short_pith_number":"pith:PLMRJUC5","schema_version":"1.0","canonical_sha256":"7ad914d05d8cfb9d70c3b27f8c0c214759337eb61a7a71056e9589a708b9d7a2","source":{"kind":"arxiv","id":"2501.06366","version":2},"attestation_state":"computed","paper":{"title":"Counterfactually Fair Reinforcement Learning via Sequential Data Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Chengchun Shi, Donglin Zeng, Jitao Wang, John D. Piette, Joshua R. Loftus, Zhenke Wu","submitted_at":"2025-01-10T22:27:44Z","abstract_excerpt":"When applied in healthcare, reinforcement learning (RL) seeks to dynamically match the right interventions to subjects to maximize population benefit. However, the learned policy may disproportionately allocate efficacious actions to one subpopulation, creating or exacerbating disparities in other socioeconomically-disadvantaged subgroups. These biases tend to occur in multi-stage decision making and can be self-perpetuating, which if unaccounted for could cause serious unintended consequences that limit access to care or treatment benefit. Counterfactual fairness (CF) offers a promising stati"},"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":"2501.06366","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-10T22:27:44Z","cross_cats_sorted":["cs.CY","cs.LG","stat.ME"],"title_canon_sha256":"c3816c3a5c4f6a0ef56b7edafcaeea2d4151549ee84c73e3ab75cc8a2852a961","abstract_canon_sha256":"ac72aa1dede5e6ae7225ca8c813f36803bacc1abe38c069deaee2f32b96f5315"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:46.481915Z","signature_b64":"3809txDnEBAt9oc9o1d2E4344gMbJon490PfQIt89KTI2QaTM4+IinUzys5V1bNRryOa3OEWVOs4Du0ByrMoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ad914d05d8cfb9d70c3b27f8c0c214759337eb61a7a71056e9589a708b9d7a2","last_reissued_at":"2026-07-05T10:00:46.481490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:46.481490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactually Fair Reinforcement Learning via Sequential Data Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Chengchun Shi, Donglin Zeng, Jitao Wang, John D. Piette, Joshua R. Loftus, Zhenke Wu","submitted_at":"2025-01-10T22:27:44Z","abstract_excerpt":"When applied in healthcare, reinforcement learning (RL) seeks to dynamically match the right interventions to subjects to maximize population benefit. However, the learned policy may disproportionately allocate efficacious actions to one subpopulation, creating or exacerbating disparities in other socioeconomically-disadvantaged subgroups. These biases tend to occur in multi-stage decision making and can be self-perpetuating, which if unaccounted for could cause serious unintended consequences that limit access to care or treatment benefit. Counterfactual fairness (CF) offers a promising stati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06366","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.06366/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":"2501.06366","created_at":"2026-07-05T10:00:46.481547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06366v2","created_at":"2026-07-05T10:00:46.481547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06366","created_at":"2026-07-05T10:00:46.481547+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLMRJUC5RT5Z","created_at":"2026-07-05T10:00:46.481547+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLMRJUC5RT5Z24GD","created_at":"2026-07-05T10:00:46.481547+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLMRJUC5","created_at":"2026-07-05T10:00:46.481547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21709","citing_title":"Residues of a tropical zeta function for convex domains","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25114","citing_title":"Counterfactually Safe Reinforcement Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21711","citing_title":"Fairness under uncertainty in sequential decisions","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5","json":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5.json","graph_json":"https://pith.science/api/pith-number/PLMRJUC5RT5Z24GDWJ7YYDBBI5/graph.json","events_json":"https://pith.science/api/pith-number/PLMRJUC5RT5Z24GDWJ7YYDBBI5/events.json","paper":"https://pith.science/paper/PLMRJUC5"},"agent_actions":{"view_html":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5","download_json":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5.json","view_paper":"https://pith.science/paper/PLMRJUC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06366&json=true","fetch_graph":"https://pith.science/api/pith-number/PLMRJUC5RT5Z24GDWJ7YYDBBI5/graph.json","fetch_events":"https://pith.science/api/pith-number/PLMRJUC5RT5Z24GDWJ7YYDBBI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5/action/storage_attestation","attest_author":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5/action/author_attestation","sign_citation":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5/action/citation_signature","submit_replication":"https://pith.science/pith/PLMRJUC5RT5Z24GDWJ7YYDBBI5/action/replication_record"}},"created_at":"2026-07-05T10:00:46.481547+00:00","updated_at":"2026-07-05T10:00:46.481547+00:00"}