{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NNOR6N4FLJXSAWCL2WLGACZTNM","short_pith_number":"pith:NNOR6N4F","canonical_record":{"source":{"id":"1806.05631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T16:17:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3010a3978e31669389274c1964efe86a097b3b4a6834cd25ab10c3a4df8833a7","abstract_canon_sha256":"30f24a5da4222a60ceac8868eb8f4ec3fc264c04fec890124f52f5cdcda4a1a6"},"schema_version":"1.0"},"canonical_sha256":"6b5d1f37855a6f20584bd596600b336b0fd94d77e67734af11f372538ef5d169","source":{"kind":"arxiv","id":"1806.05631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05631","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05631v1","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05631","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"NNOR6N4FLJXS","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NNOR6N4FLJXSAWCL","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NNOR6N4F","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NNOR6N4FLJXSAWCL2WLGACZTNM","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T16:17:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3010a3978e31669389274c1964efe86a097b3b4a6834cd25ab10c3a4df8833a7","abstract_canon_sha256":"30f24a5da4222a60ceac8868eb8f4ec3fc264c04fec890124f52f5cdcda4a1a6"},"schema_version":"1.0"},"canonical_sha256":"6b5d1f37855a6f20584bd596600b336b0fd94d77e67734af11f372538ef5d169","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:14.554080Z","signature_b64":"PDB9KHeqLnQ8Yp+44h1nZiWc2ZPlhNG4HBrU12/tC6V7+BHSu7YInZj6ZM9k2+YmAxTD7MG/tj9JRyfOKfVsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b5d1f37855a6f20584bd596600b336b0fd94d77e67734af11f372538ef5d169","last_reissued_at":"2026-05-18T00:13:14.553395Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:14.553395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05631","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":"2026-05-18T00:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ouN0onMtV1WqXkDt5FDHY6DY/+k/6JpxQ09x7P9LuH5gPpw2+wQ4xjzlfJXFWfPgUAog2VJYScng1MtSiRUHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:06:35.007778Z"},"content_sha256":"572a200f9bb7c8a74cecabbf230ef15b4bc3a077fcfefbf24c9a1d0d6fd022e0","schema_version":"1.0","event_id":"sha256:572a200f9bb7c8a74cecabbf230ef15b4bc3a077fcfefbf24c9a1d0d6fd022e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NNOR6N4FLJXSAWCL2WLGACZTNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning in POMDPs with Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Frans A. Oliehoek, Sammie Katt","submitted_at":"2018-06-14T16:17:44Z","abstract_excerpt":"The POMDP is a powerful framework for reasoning under outcome and information uncertainty, but constructing an accurate POMDP model is difficult. Bayes-Adaptive Partially Observable Markov Decision Processes (BA-POMDPs) extend POMDPs to allow the model to be learned during execution. BA-POMDPs are a Bayesian RL approach that, in principle, allows for an optimal trade-off between exploitation and exploration. Unfortunately, BA-POMDPs are currently impractical to solve for any non-trivial domain. In this paper, we extend the Monte-Carlo Tree Search method POMCP to BA-POMDPs and show that the res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05631","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":"2026-05-18T00:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WupUVRomSYC23VaA64k/DjgiX/XZYnj86RQVsIjO6/5XH4AL7dabbnMkndc5SS4lloiLworBcgpyFVb5/2M1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:06:35.008150Z"},"content_sha256":"2c34cb2b9bfd4e609d0b347224a457f90c3f3857f95b48815745868ba2fc6f12","schema_version":"1.0","event_id":"sha256:2c34cb2b9bfd4e609d0b347224a457f90c3f3857f95b48815745868ba2fc6f12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/bundle.json","state_url":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/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":"2026-07-05T11:06:35Z","links":{"resolver":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM","bundle":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/bundle.json","state":"https://pith.science/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNOR6N4FLJXSAWCL2WLGACZTNM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NNOR6N4FLJXSAWCL2WLGACZTNM","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":"30f24a5da4222a60ceac8868eb8f4ec3fc264c04fec890124f52f5cdcda4a1a6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T16:17:44Z","title_canon_sha256":"3010a3978e31669389274c1964efe86a097b3b4a6834cd25ab10c3a4df8833a7"},"schema_version":"1.0","source":{"id":"1806.05631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05631","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05631v1","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05631","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"NNOR6N4FLJXS","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NNOR6N4FLJXSAWCL","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NNOR6N4F","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:2c34cb2b9bfd4e609d0b347224a457f90c3f3857f95b48815745868ba2fc6f12","target":"graph","created_at":"2026-05-18T00:13:14Z","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":"The POMDP is a powerful framework for reasoning under outcome and information uncertainty, but constructing an accurate POMDP model is difficult. Bayes-Adaptive Partially Observable Markov Decision Processes (BA-POMDPs) extend POMDPs to allow the model to be learned during execution. BA-POMDPs are a Bayesian RL approach that, in principle, allows for an optimal trade-off between exploitation and exploration. Unfortunately, BA-POMDPs are currently impractical to solve for any non-trivial domain. In this paper, we extend the Monte-Carlo Tree Search method POMCP to BA-POMDPs and show that the res","authors_text":"Christopher Amato, Frans A. Oliehoek, Sammie Katt","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T16:17:44Z","title":"Learning in POMDPs with Monte Carlo Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05631","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":"sha256:572a200f9bb7c8a74cecabbf230ef15b4bc3a077fcfefbf24c9a1d0d6fd022e0","target":"record","created_at":"2026-05-18T00:13:14Z","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":"30f24a5da4222a60ceac8868eb8f4ec3fc264c04fec890124f52f5cdcda4a1a6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T16:17:44Z","title_canon_sha256":"3010a3978e31669389274c1964efe86a097b3b4a6834cd25ab10c3a4df8833a7"},"schema_version":"1.0","source":{"id":"1806.05631","kind":"arxiv","version":1}},"canonical_sha256":"6b5d1f37855a6f20584bd596600b336b0fd94d77e67734af11f372538ef5d169","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b5d1f37855a6f20584bd596600b336b0fd94d77e67734af11f372538ef5d169","first_computed_at":"2026-05-18T00:13:14.553395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:14.553395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PDB9KHeqLnQ8Yp+44h1nZiWc2ZPlhNG4HBrU12/tC6V7+BHSu7YInZj6ZM9k2+YmAxTD7MG/tj9JRyfOKfVsAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:14.554080Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:572a200f9bb7c8a74cecabbf230ef15b4bc3a077fcfefbf24c9a1d0d6fd022e0","sha256:2c34cb2b9bfd4e609d0b347224a457f90c3f3857f95b48815745868ba2fc6f12"],"state_sha256":"f7cb6e0c751f2ba88736f5a6af7f1231d731f571857160ab878ff63887dd650d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c4KimjZnEgesi4hIMSFZ9SaZ5lBcPDWeNomZ81JbGxeQ5m/T6JHGgajCtzGQHEibJ/I+vqSjV0NF//M/l67BAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:06:35.010090Z","bundle_sha256":"3ee1724837f7aeb257c1ef966d55c9f9efd7835065eeb74f4be6583283db52af"}}