{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IFX6NX7UB56MWW5QSANDJAAA56","short_pith_number":"pith:IFX6NX7U","schema_version":"1.0","canonical_sha256":"416fe6dff40f7ccb5bb0901a348000efab174c97bd933587c5a03b84b3deacf8","source":{"kind":"arxiv","id":"2412.17123","version":2},"attestation_state":"computed","paper":{"title":"Fairness in Reinforcement Learning with Bisimulation Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"David Meger, Doina Precup, Hanna Yurchyk, Sahand Rezaei-Shoshtari, Scott Fujimoto","submitted_at":"2024-12-22T18:23:06Z","abstract_excerpt":"Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environments. By maximizing their reward without consideration of fairness, AI agents can introduce disparities in their treatment of groups or individuals. In this paper, we establish the connection between bisimulation metrics and group fairness in reinforcement learning. We propose a novel approach that leverages bisimulation metrics to learn reward functions and observation dynamics, ensuring that learners treat groups fairly while reflecting the original problem"},"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":"2412.17123","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T18:23:06Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"aac73b9e4074afaef53f7db25cf9175f0ed335e207a4d154404709720b4a484b","abstract_canon_sha256":"74a727194351294604da3584699d2a374b6567a5fd2565ce2fb3567c5812a27d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:04.031187Z","signature_b64":"TEG13q19SNEgGrxJynq480LT/I8TGrI3yNwonP0ytg9UYBYb6YnfIkpZ80BvcaeUaPvzQNuebYSzKnil+lpZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"416fe6dff40f7ccb5bb0901a348000efab174c97bd933587c5a03b84b3deacf8","last_reissued_at":"2026-07-05T09:56:04.030698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:04.030698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairness in Reinforcement Learning with Bisimulation Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"David Meger, Doina Precup, Hanna Yurchyk, Sahand Rezaei-Shoshtari, Scott Fujimoto","submitted_at":"2024-12-22T18:23:06Z","abstract_excerpt":"Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environments. By maximizing their reward without consideration of fairness, AI agents can introduce disparities in their treatment of groups or individuals. In this paper, we establish the connection between bisimulation metrics and group fairness in reinforcement learning. We propose a novel approach that leverages bisimulation metrics to learn reward functions and observation dynamics, ensuring that learners treat groups fairly while reflecting the original problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17123","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/2412.17123/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":"2412.17123","created_at":"2026-07-05T09:56:04.030758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17123v2","created_at":"2026-07-05T09:56:04.030758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17123","created_at":"2026-07-05T09:56:04.030758+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFX6NX7UB56M","created_at":"2026-07-05T09:56:04.030758+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFX6NX7UB56MWW5Q","created_at":"2026-07-05T09:56:04.030758+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFX6NX7U","created_at":"2026-07-05T09:56:04.030758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22291","citing_title":"Long-term Fairness with Selective Labels","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56","json":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56.json","graph_json":"https://pith.science/api/pith-number/IFX6NX7UB56MWW5QSANDJAAA56/graph.json","events_json":"https://pith.science/api/pith-number/IFX6NX7UB56MWW5QSANDJAAA56/events.json","paper":"https://pith.science/paper/IFX6NX7U"},"agent_actions":{"view_html":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56","download_json":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56.json","view_paper":"https://pith.science/paper/IFX6NX7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17123&json=true","fetch_graph":"https://pith.science/api/pith-number/IFX6NX7UB56MWW5QSANDJAAA56/graph.json","fetch_events":"https://pith.science/api/pith-number/IFX6NX7UB56MWW5QSANDJAAA56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56/action/storage_attestation","attest_author":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56/action/author_attestation","sign_citation":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56/action/citation_signature","submit_replication":"https://pith.science/pith/IFX6NX7UB56MWW5QSANDJAAA56/action/replication_record"}},"created_at":"2026-07-05T09:56:04.030758+00:00","updated_at":"2026-07-05T09:56:04.030758+00:00"}