{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J5PXZ3DC5N2HFGFW4OH2RQN6VC","short_pith_number":"pith:J5PXZ3DC","canonical_record":{"source":{"id":"1902.02893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T00:30:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77c8cfe082a15229bb5e5be7b21662e9b5c94cbef2681071391d51ce9cb00675","abstract_canon_sha256":"bc11034241e102a20eb5614e023ead8a729b97169259b803d13cab8e5e224210"},"schema_version":"1.0"},"canonical_sha256":"4f5f7cec62eb747298b6e38fa8c1bea8a06c6c95311832ff575924033603c17d","source":{"kind":"arxiv","id":"1902.02893","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02893","created_at":"2026-05-17T23:54:28Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02893v1","created_at":"2026-05-17T23:54:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02893","created_at":"2026-05-17T23:54:28Z"},{"alias_kind":"pith_short_12","alias_value":"J5PXZ3DC5N2H","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J5PXZ3DC5N2HFGFW","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J5PXZ3DC","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J5PXZ3DC5N2HFGFW4OH2RQN6VC","target":"record","payload":{"canonical_record":{"source":{"id":"1902.02893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T00:30:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77c8cfe082a15229bb5e5be7b21662e9b5c94cbef2681071391d51ce9cb00675","abstract_canon_sha256":"bc11034241e102a20eb5614e023ead8a729b97169259b803d13cab8e5e224210"},"schema_version":"1.0"},"canonical_sha256":"4f5f7cec62eb747298b6e38fa8c1bea8a06c6c95311832ff575924033603c17d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:28.935573Z","signature_b64":"y8XVHqwG7OMOoSL23IR3NbJ6fNiuTWI/fIW3x9hBt0Tz638dnVRDBr1D8fOqhUt/zeToN2YK3NR35dNs+12+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f5f7cec62eb747298b6e38fa8c1bea8a06c6c95311832ff575924033603c17d","last_reissued_at":"2026-05-17T23:54:28.935137Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:28.935137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.02893","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5GRJ2jxOwi4zO5k9YaUToj+KUo7DRPL6OeHwBEIpxVI5T9XEuKfy0iGR3Wupz1v/5GQBx/V0g6h7LNCU0aUGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T03:19:23.419373Z"},"content_sha256":"66905f3d5db0e9ad6f0aea3f4268ed0303412d17e38c8c5851e288622c10695c","schema_version":"1.0","event_id":"sha256:66905f3d5db0e9ad6f0aea3f4268ed0303412d17e38c8c5851e288622c10695c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J5PXZ3DC5N2HFGFW4OH2RQN6VC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Silviu Pitis","submitted_at":"2019-02-08T00:30:53Z","abstract_excerpt":"Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor $\\gamma < 1$, or in episodic settings, with $\\gamma = 1$. While this has proven effective for specific tasks with well-defined objectives (e.g., games), it has never been established that fixed discounting is suitable for general purpose use (e.g., as a model of human preferences). This paper characterizes rationality in sequential decision making using a set of seven axioms and arrives at a form of di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02893","kind":"arxiv","version":1},"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":"2026-05-17T23:54:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyxlGCuMdsZhOc+Bhl9frVsnVrDdiEbIVe/bdlX6+kKL9BvWqwTcdHyg7cHgUUYxb+blUt/bP4whlpon+lZDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T03:19:23.419710Z"},"content_sha256":"563ec43b1ef1f6e456851f7980f47aece9d4d4a98b2f78a56f7196b12e9807d8","schema_version":"1.0","event_id":"sha256:563ec43b1ef1f6e456851f7980f47aece9d4d4a98b2f78a56f7196b12e9807d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/bundle.json","state_url":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/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":"2026-06-24T03:19:23Z","links":{"resolver":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC","bundle":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/bundle.json","state":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J5PXZ3DC5N2HFGFW4OH2RQN6VC","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":"bc11034241e102a20eb5614e023ead8a729b97169259b803d13cab8e5e224210","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T00:30:53Z","title_canon_sha256":"77c8cfe082a15229bb5e5be7b21662e9b5c94cbef2681071391d51ce9cb00675"},"schema_version":"1.0","source":{"id":"1902.02893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02893","created_at":"2026-05-17T23:54:28Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02893v1","created_at":"2026-05-17T23:54:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02893","created_at":"2026-05-17T23:54:28Z"},{"alias_kind":"pith_short_12","alias_value":"J5PXZ3DC5N2H","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J5PXZ3DC5N2HFGFW","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J5PXZ3DC","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:563ec43b1ef1f6e456851f7980f47aece9d4d4a98b2f78a56f7196b12e9807d8","target":"graph","created_at":"2026-05-17T23:54:28Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor $\\gamma < 1$, or in episodic settings, with $\\gamma = 1$. While this has proven effective for specific tasks with well-defined objectives (e.g., games), it has never been established that fixed discounting is suitable for general purpose use (e.g., as a model of human preferences). This paper characterizes rationality in sequential decision making using a set of seven axioms and arrives at a form of di","authors_text":"Silviu Pitis","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T00:30:53Z","title":"Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02893","kind":"arxiv","version":1},"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":"sha256:66905f3d5db0e9ad6f0aea3f4268ed0303412d17e38c8c5851e288622c10695c","target":"record","created_at":"2026-05-17T23:54:28Z","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":"bc11034241e102a20eb5614e023ead8a729b97169259b803d13cab8e5e224210","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T00:30:53Z","title_canon_sha256":"77c8cfe082a15229bb5e5be7b21662e9b5c94cbef2681071391d51ce9cb00675"},"schema_version":"1.0","source":{"id":"1902.02893","kind":"arxiv","version":1}},"canonical_sha256":"4f5f7cec62eb747298b6e38fa8c1bea8a06c6c95311832ff575924033603c17d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f5f7cec62eb747298b6e38fa8c1bea8a06c6c95311832ff575924033603c17d","first_computed_at":"2026-05-17T23:54:28.935137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:28.935137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y8XVHqwG7OMOoSL23IR3NbJ6fNiuTWI/fIW3x9hBt0Tz638dnVRDBr1D8fOqhUt/zeToN2YK3NR35dNs+12+AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:28.935573Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.02893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66905f3d5db0e9ad6f0aea3f4268ed0303412d17e38c8c5851e288622c10695c","sha256:563ec43b1ef1f6e456851f7980f47aece9d4d4a98b2f78a56f7196b12e9807d8"],"state_sha256":"0ce3764d724fd05e1903b9a1b51caed1d9438c8f9de085fca421972d8c233999"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fRjQfaJjxsIMQPTZRMG6Ekg6tBJ9lUMBaX8K676cI39wvaeVG4iLhA/l00IQ+LU3RwC3B6900h0Jbl0MWEOhAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T03:19:23.421614Z","bundle_sha256":"7adf5d59b447a1b9ece236200cee6830c0b587b52f96abbfc10f7f80b59e73be"}}