{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TMMF23ZN5X66GKJW2KTTOH5JNL","short_pith_number":"pith:TMMF23ZN","canonical_record":{"source":{"id":"2311.13294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T10:23:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1affa247cb395d8bd7228beec632a7215636b48c2b47050e7619ef224f5074ee","abstract_canon_sha256":"4a0b8bfd03cb5492265874c7f36f85b0d2104135c08a805d819f9af2d6bf9448"},"schema_version":"1.0"},"canonical_sha256":"9b185d6f2dedfde32936d2a7371fa96af3251d6f9686cb5712f8af293ad4ad9d","source":{"kind":"arxiv","id":"2311.13294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13294","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13294v1","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13294","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"TMMF23ZN5X66","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"TMMF23ZN5X66GKJW","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"TMMF23ZN","created_at":"2026-07-05T07:15:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TMMF23ZN5X66GKJW2KTTOH5JNL","target":"record","payload":{"canonical_record":{"source":{"id":"2311.13294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T10:23:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1affa247cb395d8bd7228beec632a7215636b48c2b47050e7619ef224f5074ee","abstract_canon_sha256":"4a0b8bfd03cb5492265874c7f36f85b0d2104135c08a805d819f9af2d6bf9448"},"schema_version":"1.0"},"canonical_sha256":"9b185d6f2dedfde32936d2a7371fa96af3251d6f9686cb5712f8af293ad4ad9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:27.303029Z","signature_b64":"2yLQcyRZkEYsuIa5iCKbhg3hFacDyBezxhEDJLjtVnKf1uEqeHaeK5Iw5rc9+mXthfiFEMx5tGJN+zD8H/k9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b185d6f2dedfde32936d2a7371fa96af3251d6f9686cb5712f8af293ad4ad9d","last_reissued_at":"2026-07-05T07:15:27.302601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:27.302601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.13294","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":"2026-07-05T07:15:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oy8PLYpAxCFTyHwXKqE2iNncxcTw1W3WoCysP31yZUd21o8K4thH7W4B4/7itq4OuxBAYWFc01cf9GVVpxaECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:21:04.403561Z"},"content_sha256":"d2316b7bee60560ecc6f98cb0d4cd0ed6d1538dc67454e08cf3c59b6232f3537","schema_version":"1.0","event_id":"sha256:d2316b7bee60560ecc6f98cb0d4cd0ed6d1538dc67454e08cf3c59b6232f3537"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TMMF23ZN5X66GKJW2KTTOH5JNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic Inference in Reinforcement Learning Done Right","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brendan O'Donoghue, Jean Tarbouriech, Tor Lattimore","submitted_at":"2023-11-22T10:23:14Z","abstract_excerpt":"A popular perspective in Reinforcement learning (RL) casts the problem as probabilistic inference on a graphical model of the Markov decision process (MDP). The core object of study is the probability of each state-action pair being visited under the optimal policy. Previous approaches to approximate this quantity can be arbitrarily poor, leading to algorithms that do not implement genuine statistical inference and consequently do not perform well in challenging problems. In this work, we undertake a rigorous Bayesian treatment of the posterior probability of state-action optimality and clarif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13294","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.13294/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":"2026-07-05T07:15:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7G0qZhk+/iY6O1FtLF14tDawbtq5b/9ynPrFgZvJSiMPuTMxFHMUiaokPCmhzk+rRrxIbbqD1y/zgZO3eRyEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:21:04.403941Z"},"content_sha256":"391724e0a85174ca0dc11139177a8c3c98e1d0e32382401381de0e3a5e57c01e","schema_version":"1.0","event_id":"sha256:391724e0a85174ca0dc11139177a8c3c98e1d0e32382401381de0e3a5e57c01e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TMMF23ZN5X66GKJW2KTTOH5JNL/bundle.json","state_url":"https://pith.science/pith/TMMF23ZN5X66GKJW2KTTOH5JNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TMMF23ZN5X66GKJW2KTTOH5JNL/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":"2026-07-07T12:21:04Z","links":{"resolver":"https://pith.science/pith/TMMF23ZN5X66GKJW2KTTOH5JNL","bundle":"https://pith.science/pith/TMMF23ZN5X66GKJW2KTTOH5JNL/bundle.json","state":"https://pith.science/pith/TMMF23ZN5X66GKJW2KTTOH5JNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TMMF23ZN5X66GKJW2KTTOH5JNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TMMF23ZN5X66GKJW2KTTOH5JNL","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":"4a0b8bfd03cb5492265874c7f36f85b0d2104135c08a805d819f9af2d6bf9448","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T10:23:14Z","title_canon_sha256":"1affa247cb395d8bd7228beec632a7215636b48c2b47050e7619ef224f5074ee"},"schema_version":"1.0","source":{"id":"2311.13294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13294","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13294v1","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13294","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"TMMF23ZN5X66","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"TMMF23ZN5X66GKJW","created_at":"2026-07-05T07:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"TMMF23ZN","created_at":"2026-07-05T07:15:27Z"}],"graph_snapshots":[{"event_id":"sha256:391724e0a85174ca0dc11139177a8c3c98e1d0e32382401381de0e3a5e57c01e","target":"graph","created_at":"2026-07-05T07:15:27Z","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/2311.13294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A popular perspective in Reinforcement learning (RL) casts the problem as probabilistic inference on a graphical model of the Markov decision process (MDP). The core object of study is the probability of each state-action pair being visited under the optimal policy. Previous approaches to approximate this quantity can be arbitrarily poor, leading to algorithms that do not implement genuine statistical inference and consequently do not perform well in challenging problems. In this work, we undertake a rigorous Bayesian treatment of the posterior probability of state-action optimality and clarif","authors_text":"Brendan O'Donoghue, Jean Tarbouriech, Tor Lattimore","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T10:23:14Z","title":"Probabilistic Inference in Reinforcement Learning Done Right"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13294","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:d2316b7bee60560ecc6f98cb0d4cd0ed6d1538dc67454e08cf3c59b6232f3537","target":"record","created_at":"2026-07-05T07:15:27Z","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":"4a0b8bfd03cb5492265874c7f36f85b0d2104135c08a805d819f9af2d6bf9448","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T10:23:14Z","title_canon_sha256":"1affa247cb395d8bd7228beec632a7215636b48c2b47050e7619ef224f5074ee"},"schema_version":"1.0","source":{"id":"2311.13294","kind":"arxiv","version":1}},"canonical_sha256":"9b185d6f2dedfde32936d2a7371fa96af3251d6f9686cb5712f8af293ad4ad9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b185d6f2dedfde32936d2a7371fa96af3251d6f9686cb5712f8af293ad4ad9d","first_computed_at":"2026-07-05T07:15:27.302601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:15:27.302601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2yLQcyRZkEYsuIa5iCKbhg3hFacDyBezxhEDJLjtVnKf1uEqeHaeK5Iw5rc9+mXthfiFEMx5tGJN+zD8H/k9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:15:27.303029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2316b7bee60560ecc6f98cb0d4cd0ed6d1538dc67454e08cf3c59b6232f3537","sha256:391724e0a85174ca0dc11139177a8c3c98e1d0e32382401381de0e3a5e57c01e"],"state_sha256":"50dca97bf503a9e1107d4ada445a306777a22ea1372f582209a70ae2004c0ed3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0zxXevgopjjlBZq9ghpNJCwWi/sO0StAyJxtxBgxZ4FTLQdkFrjB1J9bg7cjImQQEQvhJmdC8BEGCR4gEDyBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:21:04.405971Z","bundle_sha256":"161eb7b1d58bf8f75639c9b7689656a31ce7f225df49839ae235cebb4ca054b5"}}