{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NXVXCD6HBTMPFQALERRR7YUHI5","short_pith_number":"pith:NXVXCD6H","schema_version":"1.0","canonical_sha256":"6deb710fc70cd8f2c00b24631fe287475b8ada86829b78c17128429ac684317a","source":{"kind":"arxiv","id":"2602.04155","version":2},"attestation_state":"computed","paper":{"title":"Maximin Relative Improvement: Fair Learning as a Bargaining Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiwoo Han, Moulinath Banerjee, Yuekai Sun","submitted_at":"2026-02-04T02:44:56Z","abstract_excerpt":"When deploying a single predictor across multiple subpopulations, we propose a fundamentally different approach: interpreting group fairness as a bargaining problem among subpopulations. This game-theoretic perspective reveals that existing robust optimization methods such as minimizing worst-group loss or regret correspond to classical bargaining solutions and embody different fairness principles. We propose relative improvement, the ratio of actual risk reduction to potential reduction from a baseline predictor, which recovers the Kalai-Smorodinsky solution. Unlike absolute-scale methods tha"},"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":"2602.04155","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-02-04T02:44:56Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"3eab02656f5fb680e86111d3c27d01a683d7e830069539866c30ce17e9d90455","abstract_canon_sha256":"8470e20f1cf3bbd816cc36a6c9128655fe7b55ab00c6062bcadbc127d3a7c4f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:34.812478Z","signature_b64":"ZhWvbSiBfjcEpiBjgDihQFEZlJXcaS3xXLEUHKzmTe8YeFKlzNF5lUccCX/zS1TiLs4aYkrDitioTiVjuP1dCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6deb710fc70cd8f2c00b24631fe287475b8ada86829b78c17128429ac684317a","last_reissued_at":"2026-06-19T16:10:34.811998Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:34.811998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximin Relative Improvement: Fair Learning as a Bargaining Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiwoo Han, Moulinath Banerjee, Yuekai Sun","submitted_at":"2026-02-04T02:44:56Z","abstract_excerpt":"When deploying a single predictor across multiple subpopulations, we propose a fundamentally different approach: interpreting group fairness as a bargaining problem among subpopulations. This game-theoretic perspective reveals that existing robust optimization methods such as minimizing worst-group loss or regret correspond to classical bargaining solutions and embody different fairness principles. We propose relative improvement, the ratio of actual risk reduction to potential reduction from a baseline predictor, which recovers the Kalai-Smorodinsky solution. Unlike absolute-scale methods tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04155","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/2602.04155/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":"2602.04155","created_at":"2026-06-19T16:10:34.812054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.04155v2","created_at":"2026-06-19T16:10:34.812054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04155","created_at":"2026-06-19T16:10:34.812054+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXVXCD6HBTMP","created_at":"2026-06-19T16:10:34.812054+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXVXCD6HBTMPFQAL","created_at":"2026-06-19T16:10:34.812054+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXVXCD6H","created_at":"2026-06-19T16:10:34.812054+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/NXVXCD6HBTMPFQALERRR7YUHI5","json":"https://pith.science/pith/NXVXCD6HBTMPFQALERRR7YUHI5.json","graph_json":"https://pith.science/api/pith-number/NXVXCD6HBTMPFQALERRR7YUHI5/graph.json","events_json":"https://pith.science/api/pith-number/NXVXCD6HBTMPFQALERRR7YUHI5/events.json","paper":"https://pith.science/paper/NXVXCD6H"},"agent_actions":{"view_html":"https://pith.science/pith/NXVXCD6HBTMPFQALERRR7YUHI5","download_json":"https://pith.science/pith/NXVXCD6HBTMPFQALERRR7YUHI5.json","view_paper":"https://pith.science/paper/NXVXCD6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.04155&json=true","fetch_graph":"https://pith.science/api/pith-number/NXVXCD6HBTMPFQALERRR7YUHI5/graph.json","fetch_events":"https://pith.science/api/pith-number/NXVXCD6HBTMPFQALERRR7YUHI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXVXCD6HBTMPFQALERRR7YUHI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXVXCD6HBTMPFQALERRR7YUHI5/action/storage_attestation","attest_author":"https://pith.science/pith/NXVXCD6HBTMPFQALERRR7YUHI5/action/author_attestation","sign_citation":"https://pith.science/pith/NXVXCD6HBTMPFQALERRR7YUHI5/action/citation_signature","submit_replication":"https://pith.science/pith/NXVXCD6HBTMPFQALERRR7YUHI5/action/replication_record"}},"created_at":"2026-06-19T16:10:34.812054+00:00","updated_at":"2026-06-19T16:10:34.812054+00:00"}