{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DI4CJWDG6YA7HLX6SC4TP4BF5C","short_pith_number":"pith:DI4CJWDG","canonical_record":{"source":{"id":"2505.07911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T13:34:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77bc08622fb8957fc7a391463e4e91681d979adca1240e5368387fc424b53349","abstract_canon_sha256":"f665772eb5644a85d0a6d996f1371a10385bc94a0c9caf4cc80acfd0ce5697ac"},"schema_version":"1.0"},"canonical_sha256":"1a3824d866f601f3aefe90b937f025e89d392d1e562a98182a51a35144114cd7","source":{"kind":"arxiv","id":"2505.07911","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07911","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07911v1","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07911","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"DI4CJWDG6YA7","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"DI4CJWDG6YA7HLX6","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"DI4CJWDG","created_at":"2026-07-05T11:01:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DI4CJWDG6YA7HLX6SC4TP4BF5C","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T13:34:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77bc08622fb8957fc7a391463e4e91681d979adca1240e5368387fc424b53349","abstract_canon_sha256":"f665772eb5644a85d0a6d996f1371a10385bc94a0c9caf4cc80acfd0ce5697ac"},"schema_version":"1.0"},"canonical_sha256":"1a3824d866f601f3aefe90b937f025e89d392d1e562a98182a51a35144114cd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:59.476497Z","signature_b64":"1oUcFoKrn0Gu8WC50pd3Ny0qYwltnaXmQtI/Dyok0VULKUO9UiI2PZVNL6yd9baC8wy4CCbxaWr1/0peC+7BDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a3824d866f601f3aefe90b937f025e89d392d1e562a98182a51a35144114cd7","last_reissued_at":"2026-07-05T11:01:59.476023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:59.476023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07911","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":"2026-07-05T11:01:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uutn2sdVCyVrz6C6S1PPlkTtszOz0gs3vrYJRrilbHm6lM9dFsFSUHMY+j8MpBZFMKNq8cPz/cIo80i1NBCTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:28:54.912090Z"},"content_sha256":"5948d62702e9582066430cb5b97b50af2026536be0a39fb58aaea178dcf93c49","schema_version":"1.0","event_id":"sha256:5948d62702e9582066430cb5b97b50af2026536be0a39fb58aaea178dcf93c49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DI4CJWDG6YA7HLX6SC4TP4BF5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengmin Zhou, Laura Ruotsalainen, Pasi Fr\\\"anti, Ville Kyrki","submitted_at":"2025-05-12T13:34:50Z","abstract_excerpt":"Bayesian inference has many advantages in decision making of agents (e.g. robotics/simulative agent) over a regular data-driven black-box neural network: Data-efficiency, generalization, interpretability, and safety where these advantages benefit directly/indirectly from the uncertainty quantification of Bayesian inference. However, there are few comprehensive reviews to summarize the progress of Bayesian inference on reinforcement learning (RL) for decision making to give researchers a systematic understanding. This paper focuses on combining Bayesian inference with RL that nowadays is an imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07911","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/2505.07911/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":"2026-07-05T11:01:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z0LeD/GTI3gPcSC2BOnix73tpKWTXSNADZQmXAlLH/dR0xoF7S17NQuWLWfnxTTTALkuqjoq7tFT3W0Ual+BCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:28:54.912482Z"},"content_sha256":"ea43e36e1354aac48adc6c98d7f3254cb5f026ced363138a4e55a58ff826de76","schema_version":"1.0","event_id":"sha256:ea43e36e1354aac48adc6c98d7f3254cb5f026ced363138a4e55a58ff826de76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DI4CJWDG6YA7HLX6SC4TP4BF5C/bundle.json","state_url":"https://pith.science/pith/DI4CJWDG6YA7HLX6SC4TP4BF5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DI4CJWDG6YA7HLX6SC4TP4BF5C/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":"2026-07-06T23:28:54Z","links":{"resolver":"https://pith.science/pith/DI4CJWDG6YA7HLX6SC4TP4BF5C","bundle":"https://pith.science/pith/DI4CJWDG6YA7HLX6SC4TP4BF5C/bundle.json","state":"https://pith.science/pith/DI4CJWDG6YA7HLX6SC4TP4BF5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DI4CJWDG6YA7HLX6SC4TP4BF5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DI4CJWDG6YA7HLX6SC4TP4BF5C","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":"f665772eb5644a85d0a6d996f1371a10385bc94a0c9caf4cc80acfd0ce5697ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T13:34:50Z","title_canon_sha256":"77bc08622fb8957fc7a391463e4e91681d979adca1240e5368387fc424b53349"},"schema_version":"1.0","source":{"id":"2505.07911","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07911","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07911v1","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07911","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"DI4CJWDG6YA7","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"DI4CJWDG6YA7HLX6","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"DI4CJWDG","created_at":"2026-07-05T11:01:59Z"}],"graph_snapshots":[{"event_id":"sha256:ea43e36e1354aac48adc6c98d7f3254cb5f026ced363138a4e55a58ff826de76","target":"graph","created_at":"2026-07-05T11:01:59Z","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/2505.07911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bayesian inference has many advantages in decision making of agents (e.g. robotics/simulative agent) over a regular data-driven black-box neural network: Data-efficiency, generalization, interpretability, and safety where these advantages benefit directly/indirectly from the uncertainty quantification of Bayesian inference. However, there are few comprehensive reviews to summarize the progress of Bayesian inference on reinforcement learning (RL) for decision making to give researchers a systematic understanding. This paper focuses on combining Bayesian inference with RL that nowadays is an imp","authors_text":"Chengmin Zhou, Laura Ruotsalainen, Pasi Fr\\\"anti, Ville Kyrki","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T13:34:50Z","title":"Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07911","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":"sha256:5948d62702e9582066430cb5b97b50af2026536be0a39fb58aaea178dcf93c49","target":"record","created_at":"2026-07-05T11:01:59Z","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":"f665772eb5644a85d0a6d996f1371a10385bc94a0c9caf4cc80acfd0ce5697ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T13:34:50Z","title_canon_sha256":"77bc08622fb8957fc7a391463e4e91681d979adca1240e5368387fc424b53349"},"schema_version":"1.0","source":{"id":"2505.07911","kind":"arxiv","version":1}},"canonical_sha256":"1a3824d866f601f3aefe90b937f025e89d392d1e562a98182a51a35144114cd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a3824d866f601f3aefe90b937f025e89d392d1e562a98182a51a35144114cd7","first_computed_at":"2026-07-05T11:01:59.476023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:59.476023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1oUcFoKrn0Gu8WC50pd3Ny0qYwltnaXmQtI/Dyok0VULKUO9UiI2PZVNL6yd9baC8wy4CCbxaWr1/0peC+7BDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:59.476497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07911","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5948d62702e9582066430cb5b97b50af2026536be0a39fb58aaea178dcf93c49","sha256:ea43e36e1354aac48adc6c98d7f3254cb5f026ced363138a4e55a58ff826de76"],"state_sha256":"71186667338467637e4ac37653b73a5858475b286b3e10c36d76714ecf3579c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hmUApTN/s9As6PTxbt0DWSJ7Do70W9nghB5h20q5wU95USfPD82TI5ej2nD901mdeA6OALN3ROn/JnzSdEl/AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:28:54.914457Z","bundle_sha256":"6d9c5962941c1a7b92240b06c31602336481c9384a1308e374a7110b4f59ea3e"}}