{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:66BGHV6MLUZYOKPTG4444MDKH6","short_pith_number":"pith:66BGHV6M","canonical_record":{"source":{"id":"2406.02456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T16:21:14Z","cross_cats_sorted":[],"title_canon_sha256":"56d423a8f1372dd87640274a9b705bd01fc797e4970ff1a9dd28abafd93004c2","abstract_canon_sha256":"9ed94bb698c7b25364259d4a7d0e80b6d6f7bce84b1ebca91b06ce955d910fdf"},"schema_version":"1.0"},"canonical_sha256":"f78263d7cc5d338729f33739ce306a3f91ca28a4e84386c8d1243393da33523d","source":{"kind":"arxiv","id":"2406.02456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02456","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02456v1","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02456","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"66BGHV6MLUZY","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"66BGHV6MLUZYOKPT","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"66BGHV6M","created_at":"2026-07-05T08:27:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:66BGHV6MLUZYOKPTG4444MDKH6","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T16:21:14Z","cross_cats_sorted":[],"title_canon_sha256":"56d423a8f1372dd87640274a9b705bd01fc797e4970ff1a9dd28abafd93004c2","abstract_canon_sha256":"9ed94bb698c7b25364259d4a7d0e80b6d6f7bce84b1ebca91b06ce955d910fdf"},"schema_version":"1.0"},"canonical_sha256":"f78263d7cc5d338729f33739ce306a3f91ca28a4e84386c8d1243393da33523d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:20.035583Z","signature_b64":"r1QbOfXh1YDbrzQtgq6hqNi/h88qVqaqPhW406Eq7DhLPWhUMw4wZh5+dP1p5sjArJLOXwEYKX4YepxO49m8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f78263d7cc5d338729f33739ce306a3f91ca28a4e84386c8d1243393da33523d","last_reissued_at":"2026-07-05T08:27:20.035134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:20.035134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02456","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":"2026-07-05T08:27:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/IfBz6kZr8PaHHljf2BjnUVxntahEv/EA4aLea3mssSZkGlWzir/2yzv5dc3jBf3v6yLIAv4UKYuU2YVDOQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:10:04.799157Z"},"content_sha256":"0f3999038d3f33be049b3ff2c9cdb22e90a6da110df71ada8b9d340ae8970376","schema_version":"1.0","event_id":"sha256:0f3999038d3f33be049b3ff2c9cdb22e90a6da110df71ada8b9d340ae8970376"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:66BGHV6MLUZYOKPTG4444MDKH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"A. Aldo Faisal, Filippo Valdettaro","submitted_at":"2024-06-04T16:21:14Z","abstract_excerpt":"We address the challenge of quantifying Bayesian uncertainty and incorporating it in offline use cases of finite-state Markov Decision Processes (MDPs) with unknown dynamics. Our approach provides a principled method to disentangle epistemic and aleatoric uncertainty, and a novel technique to find policies that optimise Bayesian posterior expected value without relying on strong assumptions about the MDP's posterior distribution. First, we utilise standard Bayesian reinforcement learning methods to capture the posterior uncertainty in MDP parameters based on available data. We then analyticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02456","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/2406.02456/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":"2026-07-05T08:27:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"irakVUbusFRFpKn4NgEuNG/+w6WEayLS5+4RnfPXZ1IbdXJ7imGiaNZvcYTQ2OAKWZXIdcw35oURy/xrx9tHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:10:04.799651Z"},"content_sha256":"7aefda621232077a27fe674ab0b87a4e5883116cda32ab373ca0b7fed0af90eb","schema_version":"1.0","event_id":"sha256:7aefda621232077a27fe674ab0b87a4e5883116cda32ab373ca0b7fed0af90eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/66BGHV6MLUZYOKPTG4444MDKH6/bundle.json","state_url":"https://pith.science/pith/66BGHV6MLUZYOKPTG4444MDKH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/66BGHV6MLUZYOKPTG4444MDKH6/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":"2026-08-23T17:10:04Z","links":{"resolver":"https://pith.science/pith/66BGHV6MLUZYOKPTG4444MDKH6","bundle":"https://pith.science/pith/66BGHV6MLUZYOKPTG4444MDKH6/bundle.json","state":"https://pith.science/pith/66BGHV6MLUZYOKPTG4444MDKH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/66BGHV6MLUZYOKPTG4444MDKH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:66BGHV6MLUZYOKPTG4444MDKH6","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":"9ed94bb698c7b25364259d4a7d0e80b6d6f7bce84b1ebca91b06ce955d910fdf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T16:21:14Z","title_canon_sha256":"56d423a8f1372dd87640274a9b705bd01fc797e4970ff1a9dd28abafd93004c2"},"schema_version":"1.0","source":{"id":"2406.02456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02456","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02456v1","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02456","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"66BGHV6MLUZY","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"66BGHV6MLUZYOKPT","created_at":"2026-07-05T08:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"66BGHV6M","created_at":"2026-07-05T08:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:7aefda621232077a27fe674ab0b87a4e5883116cda32ab373ca0b7fed0af90eb","target":"graph","created_at":"2026-07-05T08:27:20Z","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/2406.02456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the challenge of quantifying Bayesian uncertainty and incorporating it in offline use cases of finite-state Markov Decision Processes (MDPs) with unknown dynamics. Our approach provides a principled method to disentangle epistemic and aleatoric uncertainty, and a novel technique to find policies that optimise Bayesian posterior expected value without relying on strong assumptions about the MDP's posterior distribution. First, we utilise standard Bayesian reinforcement learning methods to capture the posterior uncertainty in MDP parameters based on available data. We then analyticall","authors_text":"A. Aldo Faisal, Filippo Valdettaro","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T16:21:14Z","title":"Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02456","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":"sha256:0f3999038d3f33be049b3ff2c9cdb22e90a6da110df71ada8b9d340ae8970376","target":"record","created_at":"2026-07-05T08:27:20Z","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":"9ed94bb698c7b25364259d4a7d0e80b6d6f7bce84b1ebca91b06ce955d910fdf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T16:21:14Z","title_canon_sha256":"56d423a8f1372dd87640274a9b705bd01fc797e4970ff1a9dd28abafd93004c2"},"schema_version":"1.0","source":{"id":"2406.02456","kind":"arxiv","version":1}},"canonical_sha256":"f78263d7cc5d338729f33739ce306a3f91ca28a4e84386c8d1243393da33523d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f78263d7cc5d338729f33739ce306a3f91ca28a4e84386c8d1243393da33523d","first_computed_at":"2026-07-05T08:27:20.035134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:20.035134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r1QbOfXh1YDbrzQtgq6hqNi/h88qVqaqPhW406Eq7DhLPWhUMw4wZh5+dP1p5sjArJLOXwEYKX4YepxO49m8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:20.035583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f3999038d3f33be049b3ff2c9cdb22e90a6da110df71ada8b9d340ae8970376","sha256:7aefda621232077a27fe674ab0b87a4e5883116cda32ab373ca0b7fed0af90eb"],"state_sha256":"f3d84110fe132e40d6d56dbd997239eeee1d4d5851da367402545c58196a9ed4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1WKyfRj9mvOUn21yj3ZDxqI4gZj/kEuCg3onnmvmYSX5gMgsFzfSlmpPw+1khhAqWBtK3Rt8GSqhh8uC3CDLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:10:04.803481Z","bundle_sha256":"0bead08ba98e4a7b238c7817dd32607283d9a779624aa76f9ac7773c6abb0314"}}