{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UDZB46TMEOXHDVD47MKPGO2GN2","short_pith_number":"pith:UDZB46TM","canonical_record":{"source":{"id":"1811.05612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-14T02:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"65f0cb4907b5b577ce8b5d38fa4556171d3c1896451a7dd9489fb18de3ca361a","abstract_canon_sha256":"048126a7a5dbcfb82c8c0e0d683db81e4d689dc65782324589a67fd9da0e4a17"},"schema_version":"1.0"},"canonical_sha256":"a0f21e7a6c23ae71d47cfb14f33b466e9503c5ea0a6580fcab13e5075ba90d9f","source":{"kind":"arxiv","id":"1811.05612","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05612","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05612v1","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05612","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"UDZB46TMEOXH","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UDZB46TMEOXHDVD4","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UDZB46TM","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UDZB46TMEOXHDVD47MKPGO2GN2","target":"record","payload":{"canonical_record":{"source":{"id":"1811.05612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-14T02:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"65f0cb4907b5b577ce8b5d38fa4556171d3c1896451a7dd9489fb18de3ca361a","abstract_canon_sha256":"048126a7a5dbcfb82c8c0e0d683db81e4d689dc65782324589a67fd9da0e4a17"},"schema_version":"1.0"},"canonical_sha256":"a0f21e7a6c23ae71d47cfb14f33b466e9503c5ea0a6580fcab13e5075ba90d9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:42.531051Z","signature_b64":"1YKDRddDhGWNU8VX6XCPxKCVJdTv5lPyQoeMMYgc9AeRI/Tvo2otYBU9ozw0Am1WGyNA0hZ1DN7KBWKhzyfxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f21e7a6c23ae71d47cfb14f33b466e9503c5ea0a6580fcab13e5075ba90d9f","last_reissued_at":"2026-05-18T00:00:42.530588Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:42.530588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.05612","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":"2026-05-18T00:00:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPpr5zQnaKNkULD2XhvoYmNtUwHgUnShDdEU/4D/ZaTXZGSLKOQ7EZZcnBmYdlYChnm0ACtfEySXziuGFWknAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:17:48.481867Z"},"content_sha256":"65ca0bb76563b46b2d1bf164d26906c92f46285c47ade1b0995a50b80c645264","schema_version":"1.0","event_id":"sha256:65ca0bb76563b46b2d1bf164d26906c92f46285c47ade1b0995a50b80c645264"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UDZB46TMEOXHDVD47MKPGO2GN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Reinforcement Learning in Factored POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Frans Oliehoek, Sammie Katt","submitted_at":"2018-11-14T02:47:05Z","abstract_excerpt":"Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning. Typical approaches, however, either assume a fully observable environment or scale poorly. This work introduces the Factored Bayes-Adaptive POMDP model, a framework that is able to exploit the underlying structure while learning the dynamics in partially observable systems. We also present a belief tracking method to approximate the joint posterior over state and model variables, and an adaptation of the Monte-Carlo Tree Search solution method, which together are capable of so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05612","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":"2026-05-18T00:00:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5lSG2vmAYiCtvYKY9YxIe5HTTnFFMU/UrCC+wz6xnZE0LvP9qMB9s4jno4mbc/Q6nE3mTwroqeMnburPMve1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:17:48.482297Z"},"content_sha256":"e1b86976a2454d2f715c6319f9f6a7b1bf4c51ed18daa23624c5df95bc2f2bb8","schema_version":"1.0","event_id":"sha256:e1b86976a2454d2f715c6319f9f6a7b1bf4c51ed18daa23624c5df95bc2f2bb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/bundle.json","state_url":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDZB46TMEOXHDVD47MKPGO2GN2/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":"2026-07-05T10:17:48Z","links":{"resolver":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2","bundle":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/bundle.json","state":"https://pith.science/pith/UDZB46TMEOXHDVD47MKPGO2GN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDZB46TMEOXHDVD47MKPGO2GN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UDZB46TMEOXHDVD47MKPGO2GN2","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":"048126a7a5dbcfb82c8c0e0d683db81e4d689dc65782324589a67fd9da0e4a17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-14T02:47:05Z","title_canon_sha256":"65f0cb4907b5b577ce8b5d38fa4556171d3c1896451a7dd9489fb18de3ca361a"},"schema_version":"1.0","source":{"id":"1811.05612","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05612","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05612v1","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05612","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"UDZB46TMEOXH","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UDZB46TMEOXHDVD4","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UDZB46TM","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:e1b86976a2454d2f715c6319f9f6a7b1bf4c51ed18daa23624c5df95bc2f2bb8","target":"graph","created_at":"2026-05-18T00:00:42Z","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":"Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning. Typical approaches, however, either assume a fully observable environment or scale poorly. This work introduces the Factored Bayes-Adaptive POMDP model, a framework that is able to exploit the underlying structure while learning the dynamics in partially observable systems. We also present a belief tracking method to approximate the joint posterior over state and model variables, and an adaptation of the Monte-Carlo Tree Search solution method, which together are capable of so","authors_text":"Christopher Amato, Frans Oliehoek, Sammie Katt","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-14T02:47:05Z","title":"Bayesian Reinforcement Learning in Factored POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05612","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":"sha256:65ca0bb76563b46b2d1bf164d26906c92f46285c47ade1b0995a50b80c645264","target":"record","created_at":"2026-05-18T00:00:42Z","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":"048126a7a5dbcfb82c8c0e0d683db81e4d689dc65782324589a67fd9da0e4a17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-14T02:47:05Z","title_canon_sha256":"65f0cb4907b5b577ce8b5d38fa4556171d3c1896451a7dd9489fb18de3ca361a"},"schema_version":"1.0","source":{"id":"1811.05612","kind":"arxiv","version":1}},"canonical_sha256":"a0f21e7a6c23ae71d47cfb14f33b466e9503c5ea0a6580fcab13e5075ba90d9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0f21e7a6c23ae71d47cfb14f33b466e9503c5ea0a6580fcab13e5075ba90d9f","first_computed_at":"2026-05-18T00:00:42.530588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:42.530588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1YKDRddDhGWNU8VX6XCPxKCVJdTv5lPyQoeMMYgc9AeRI/Tvo2otYBU9ozw0Am1WGyNA0hZ1DN7KBWKhzyfxCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:42.531051Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.05612","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65ca0bb76563b46b2d1bf164d26906c92f46285c47ade1b0995a50b80c645264","sha256:e1b86976a2454d2f715c6319f9f6a7b1bf4c51ed18daa23624c5df95bc2f2bb8"],"state_sha256":"f46eccc8f9bbb4c527f4f04de40e4813619aaa14f1de709cab58936700ffc915"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W6/BueuteMGosjGNrB89MHSPTQ4xVLqVq2bev4KvKy6t/rf75nxTjwSlhsdzFP0aJUXxGca8w1yJq3t7hyrGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T10:17:48.484522Z","bundle_sha256":"9fbbf0bbadb1b383be216e0f36109e2d6f566563e73210a5943f12c1e7327489"}}