{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QHROLRYYGJG4YKOPP4AGJLI32N","short_pith_number":"pith:QHROLRYY","canonical_record":{"source":{"id":"1611.03071","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T20:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"9d8e73fdcd3ef528f758907f03213933faba9f1c1d2b027ae05baf8bfebc2c60","abstract_canon_sha256":"edff5ff4659287bcb215263d41e0e75e4959613eee57477966f88323205cdc80"},"schema_version":"1.0"},"canonical_sha256":"81e2e5c718324dcc29cf7f0064ad1bd36748de95c690a84e8e896ae00c8a4994","source":{"kind":"arxiv","id":"1611.03071","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QHROLRYYGJG4YKOPP4AGJLI32N","target":"record","payload":{"canonical_record":{"source":{"id":"1611.03071","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T20:19:45Z","cross_cats_sorted":[],"title_canon_sha256":"9d8e73fdcd3ef528f758907f03213933faba9f1c1d2b027ae05baf8bfebc2c60","abstract_canon_sha256":"edff5ff4659287bcb215263d41e0e75e4959613eee57477966f88323205cdc80"},"schema_version":"1.0"},"canonical_sha256":"81e2e5c718324dcc29cf7f0064ad1bd36748de95c690a84e8e896ae00c8a4994","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:36.248297Z","signature_b64":"5j2JObtu/3DQElihC+XtfdyvepSac6hwQZkRbnlOyDYj3saVbG4KZZ129G+i6eszRpYkjBBY1dqxvcc0+GCtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81e2e5c718324dcc29cf7f0064ad1bd36748de95c690a84e8e896ae00c8a4994","last_reissued_at":"2026-05-18T00:38:36.247839Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:36.247839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.03071","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5LIfFz4NYTQ7Pxmopy5DsY6GLJKfUP+pTrdEavrWVH8Fo8fZIQmU6z5fNWJwXcMgwFOcjW9zvqNNoDTofb1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:59:57.040783Z"},"content_sha256":"c825b10ab0b0f93c10e3b6ef242836a83517ae1f17197d8824891a74a8cbf7eb","schema_version":"1.0","event_id":"sha256:c825b10ab0b0f93c10e3b6ef242836a83517ae1f17197d8824891a74a8cbf7eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QHROLRYYGJG4YKOPP4AGJLI32N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fairness in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Jamie Morgenstern, Matthew Joseph, Michael Kearns, Shahin Jabbari","submitted_at":"2016-11-09T20:19:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03071","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:38:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lM7Lk71Hrj/p1lcbw/opiKu1iHBOwzzkblXfF4yODLPaTl2Bl2MlkRs8m3ONhobw+9zxoiv5HBaeZ/ab3cI2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:59:57.041407Z"},"content_sha256":"5a4d58c95fcaf83ab4cbfbaf363120614d33fcdcfe369412bcc4297ca5f65052","schema_version":"1.0","event_id":"sha256:5a4d58c95fcaf83ab4cbfbaf363120614d33fcdcfe369412bcc4297ca5f65052"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHROLRYYGJG4YKOPP4AGJLI32N/bundle.json","state_url":"https://pith.science/pith/QHROLRYYGJG4YKOPP4AGJLI32N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHROLRYYGJG4YKOPP4AGJLI32N/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":"2026-05-30T12:59:57Z","links":{"resolver":"https://pith.science/pith/QHROLRYYGJG4YKOPP4AGJLI32N","bundle":"https://pith.science/pith/QHROLRYYGJG4YKOPP4AGJLI32N/bundle.json","state":"https://pith.science/pith/QHROLRYYGJG4YKOPP4AGJLI32N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHROLRYYGJG4YKOPP4AGJLI32N/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xv0WVhkxranO25ccYyIGiYuNwEyc19u3odPXOo5PqiHrJvZzuiOeFs/TCT9rS8TsMTf0mgoflz/S4j18YRpNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:59:57.044523Z","bundle_sha256":"f987b24067edd8ad95e4910c3c6baefb09eec754ac4f9c366042519e5145f832"}}