{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QHROLRYYGJG4YKOPP4AGJLI32N","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":"edff5ff4659287bcb215263d41e0e75e4959613eee57477966f88323205cdc80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T20:19:45Z","title_canon_sha256":"9d8e73fdcd3ef528f758907f03213933faba9f1c1d2b027ae05baf8bfebc2c60"},"schema_version":"1.0","source":{"id":"1611.03071","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.03071","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"arxiv_version","alias_value":"1611.03071v4","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.03071","created_at":"2026-05-18T00:38:36Z"},{"alias_kind":"pith_short_12","alias_value":"QHROLRYYGJG4","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"QHROLRYYGJG4YKOP","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"QHROLRYY","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:5a4d58c95fcaf83ab4cbfbaf363120614d33fcdcfe369412bcc4297ca5f65052","target":"graph","created_at":"2026-05-18T00:38:36Z","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"},"paper":{"abstract_excerpt":"We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another if the long-term (discounted) reward of choosing the latter action is higher. Our first result is negative: despite the fact that fairness is consistent with the optimal policy, any learning algorithm satisfying fairness must take time exponential in the number of states to achieve non-trivial approximation to the optimal policy. We then provide a provably fa","authors_text":"Aaron Roth, Jamie Morgenstern, Matthew Joseph, Michael Kearns, Shahin Jabbari","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T20:19:45Z","title":"Fairness in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03071","kind":"arxiv","version":4},"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:c825b10ab0b0f93c10e3b6ef242836a83517ae1f17197d8824891a74a8cbf7eb","target":"record","created_at":"2026-05-18T00:38:36Z","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":"edff5ff4659287bcb215263d41e0e75e4959613eee57477966f88323205cdc80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T20:19:45Z","title_canon_sha256":"9d8e73fdcd3ef528f758907f03213933faba9f1c1d2b027ae05baf8bfebc2c60"},"schema_version":"1.0","source":{"id":"1611.03071","kind":"arxiv","version":4}},"canonical_sha256":"81e2e5c718324dcc29cf7f0064ad1bd36748de95c690a84e8e896ae00c8a4994","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81e2e5c718324dcc29cf7f0064ad1bd36748de95c690a84e8e896ae00c8a4994","first_computed_at":"2026-05-18T00:38:36.247839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:36.247839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5j2JObtu/3DQElihC+XtfdyvepSac6hwQZkRbnlOyDYj3saVbG4KZZ129G+i6eszRpYkjBBY1dqxvcc0+GCtCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:36.248297Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.03071","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c825b10ab0b0f93c10e3b6ef242836a83517ae1f17197d8824891a74a8cbf7eb","sha256:5a4d58c95fcaf83ab4cbfbaf363120614d33fcdcfe369412bcc4297ca5f65052"],"state_sha256":"1a0fe6c16c2d7feb77e63c1a3e93c04c19a1a5e9b8ddaaa467fe22e4dbe18697"}