{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A7ANV5TCL4ZPP7E2TPVJKMD3FR","short_pith_number":"pith:A7ANV5TC","canonical_record":{"source":{"id":"2208.12584","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-26T11:01:55Z","cross_cats_sorted":["cs.CY","cs.GT","cs.MA"],"title_canon_sha256":"50db9c6bb2524740bdff7c9173d73ad2840c6ab8c5503061b0ae79047c7196a6","abstract_canon_sha256":"8015b1bfb0e5cd6a998754a66c673e5f80f2d8d8c91174d739c7ff81b9428498"},"schema_version":"1.0"},"canonical_sha256":"07c0daf6625f32f7fc9a9bea95307b2c4ed32eddf120049258a3168f3446ec73","source":{"kind":"arxiv","id":"2208.12584","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12584","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12584v2","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12584","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"A7ANV5TCL4ZP","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"A7ANV5TCL4ZPP7E2","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"A7ANV5TC","created_at":"2026-07-05T05:38:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A7ANV5TCL4ZPP7E2TPVJKMD3FR","target":"record","payload":{"canonical_record":{"source":{"id":"2208.12584","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-26T11:01:55Z","cross_cats_sorted":["cs.CY","cs.GT","cs.MA"],"title_canon_sha256":"50db9c6bb2524740bdff7c9173d73ad2840c6ab8c5503061b0ae79047c7196a6","abstract_canon_sha256":"8015b1bfb0e5cd6a998754a66c673e5f80f2d8d8c91174d739c7ff81b9428498"},"schema_version":"1.0"},"canonical_sha256":"07c0daf6625f32f7fc9a9bea95307b2c4ed32eddf120049258a3168f3446ec73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:28.770363Z","signature_b64":"egxT3lhK4NRbW3kZwfLA1kTUgSr/f1jvs4Og+YsLvp+dSIYOlPsgoz28+3RDlQLTQOwiId8Wrs99INd0c875BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07c0daf6625f32f7fc9a9bea95307b2c4ed32eddf120049258a3168f3446ec73","last_reissued_at":"2026-07-05T05:38:28.769928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:28.769928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.12584","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"99nVjJeoEVMA29uU/RYT7s1w5dvc/4CHZnhNnldLnsqzPsNmge47oMs1EaxBmRU//8cPVf4gIMiLmjpkiFy0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T11:25:25.417554Z"},"content_sha256":"fa9914d70a177c06ee885217d2f10b73db8c3cad93ff482ec4ce266568f52936","schema_version":"1.0","event_id":"sha256:fa9914d70a177c06ee885217d2f10b73db8c3cad93ff482ec4ce266568f52936"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A7ANV5TCL4ZPP7E2TPVJKMD3FR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Socially Fair Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Debmalya Mandal, Jiarui Gan","submitted_at":"2022-08-26T11:01:55Z","abstract_excerpt":"We consider the problem of episodic reinforcement learning where there are multiple stakeholders with different reward functions. Our goal is to output a policy that is socially fair with respect to different reward functions. Prior works have proposed different objectives that a fair policy must optimize including minimum welfare, and generalized Gini welfare. We first take an axiomatic view of the problem, and propose four axioms that any such fair objective must satisfy. We show that the Nash social welfare is the unique objective that uniquely satisfies all four objectives, whereas prior o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12584","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/2208.12584/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WfjHutPqRTZqMhVjX1xymnc8AP7ozfKuBVZMc1dUtsFoOSqIG1/oeGCjzdgLhmNpJnClzpCgnKaiWUUX81sMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T11:25:25.418531Z"},"content_sha256":"7e94499bc41c63a5b9478ee1de04e9012b6b39587018ab79f1d47288daa26c86","schema_version":"1.0","event_id":"sha256:7e94499bc41c63a5b9478ee1de04e9012b6b39587018ab79f1d47288daa26c86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A7ANV5TCL4ZPP7E2TPVJKMD3FR/bundle.json","state_url":"https://pith.science/pith/A7ANV5TCL4ZPP7E2TPVJKMD3FR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A7ANV5TCL4ZPP7E2TPVJKMD3FR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T11:25:25Z","links":{"resolver":"https://pith.science/pith/A7ANV5TCL4ZPP7E2TPVJKMD3FR","bundle":"https://pith.science/pith/A7ANV5TCL4ZPP7E2TPVJKMD3FR/bundle.json","state":"https://pith.science/pith/A7ANV5TCL4ZPP7E2TPVJKMD3FR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A7ANV5TCL4ZPP7E2TPVJKMD3FR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A7ANV5TCL4ZPP7E2TPVJKMD3FR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8015b1bfb0e5cd6a998754a66c673e5f80f2d8d8c91174d739c7ff81b9428498","cross_cats_sorted":["cs.CY","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-26T11:01:55Z","title_canon_sha256":"50db9c6bb2524740bdff7c9173d73ad2840c6ab8c5503061b0ae79047c7196a6"},"schema_version":"1.0","source":{"id":"2208.12584","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12584","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12584v2","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12584","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"A7ANV5TCL4ZP","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"A7ANV5TCL4ZPP7E2","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"A7ANV5TC","created_at":"2026-07-05T05:38:28Z"}],"graph_snapshots":[{"event_id":"sha256:7e94499bc41c63a5b9478ee1de04e9012b6b39587018ab79f1d47288daa26c86","target":"graph","created_at":"2026-07-05T05:38:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.12584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of episodic reinforcement learning where there are multiple stakeholders with different reward functions. Our goal is to output a policy that is socially fair with respect to different reward functions. Prior works have proposed different objectives that a fair policy must optimize including minimum welfare, and generalized Gini welfare. We first take an axiomatic view of the problem, and propose four axioms that any such fair objective must satisfy. We show that the Nash social welfare is the unique objective that uniquely satisfies all four objectives, whereas prior o","authors_text":"Debmalya Mandal, Jiarui Gan","cross_cats":["cs.CY","cs.GT","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-26T11:01:55Z","title":"Socially Fair Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12584","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fa9914d70a177c06ee885217d2f10b73db8c3cad93ff482ec4ce266568f52936","target":"record","created_at":"2026-07-05T05:38:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8015b1bfb0e5cd6a998754a66c673e5f80f2d8d8c91174d739c7ff81b9428498","cross_cats_sorted":["cs.CY","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-26T11:01:55Z","title_canon_sha256":"50db9c6bb2524740bdff7c9173d73ad2840c6ab8c5503061b0ae79047c7196a6"},"schema_version":"1.0","source":{"id":"2208.12584","kind":"arxiv","version":2}},"canonical_sha256":"07c0daf6625f32f7fc9a9bea95307b2c4ed32eddf120049258a3168f3446ec73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07c0daf6625f32f7fc9a9bea95307b2c4ed32eddf120049258a3168f3446ec73","first_computed_at":"2026-07-05T05:38:28.769928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:28.769928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"egxT3lhK4NRbW3kZwfLA1kTUgSr/f1jvs4Og+YsLvp+dSIYOlPsgoz28+3RDlQLTQOwiId8Wrs99INd0c875BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:28.770363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.12584","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa9914d70a177c06ee885217d2f10b73db8c3cad93ff482ec4ce266568f52936","sha256:7e94499bc41c63a5b9478ee1de04e9012b6b39587018ab79f1d47288daa26c86"],"state_sha256":"35d3aeba5302bf64b62f8706447a5c50f9a7f6e231afa2a35e8e26cea2373f87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7EdTlEE0zXpBtu/XuvVnSyHKaEmNJuW9mXr8XWRPhg+f8WqtYfmJMGSXGtqFfdFubGphhaopxG6BKhWTBYeyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T11:25:25.494479Z","bundle_sha256":"bcadfc02aa94dff23fdba5a4f5376d61765ba044b3b1cee00e6a01f5013b62cb"}}