{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:HSSZPTVPAVZRR45SAY6A6E3U2P","short_pith_number":"pith:HSSZPTVP","canonical_record":{"source":{"id":"1202.3699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","cross_cats_sorted":[],"title_canon_sha256":"0cb1178f66869cc9bdf9f57cc67d3032fa3ec16b6d612ea6fcf8644a26a4e23e","abstract_canon_sha256":"e3537fdf202976c8fe777234f8448121f5fbb8ab5edf24c7023b1f8dd26ee30c"},"schema_version":"1.0"},"canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","source":{"kind":"arxiv","id":"1202.3699","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.3699","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"1202.3699v1","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3699","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"HSSZPTVPAVZR","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"HSSZPTVPAVZRR45S","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"HSSZPTVP","created_at":"2026-05-18T12:27:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:HSSZPTVPAVZRR45SAY6A6E3U2P","target":"record","payload":{"canonical_record":{"source":{"id":"1202.3699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","cross_cats_sorted":[],"title_canon_sha256":"0cb1178f66869cc9bdf9f57cc67d3032fa3ec16b6d612ea6fcf8644a26a4e23e","abstract_canon_sha256":"e3537fdf202976c8fe777234f8448121f5fbb8ab5edf24c7023b1f8dd26ee30c"},"schema_version":"1.0"},"canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:02:03.522164Z","signature_b64":"RK0LRkrmEz+twuaidVGdDlb/AURQbGUw2V+j7K/phfnp3Yw4LPyPoRfS337xWspMKD76kHeCslA6UkRhUF1qCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","last_reissued_at":"2026-05-18T04:02:03.521556Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:02:03.521556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1202.3699","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":"2026-05-18T04:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6I2oYPeNcJO0l01CYOw50+oCAwrrjP3irbwPqHqc9T7J9L0PwV+IVwgOlRHeRwbEkAVviL3Z5i0q2iznDyp+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T14:27:53.190697Z"},"content_sha256":"bf0c8fabb4230c68dcda92c060e7bfc36aa6a8424c30b37dcc20bd99d503c585","schema_version":"1.0","event_id":"sha256:bf0c8fabb4230c68dcda92c060e7bfc36aa6a8424c30b37dcc20bd99d503c585"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:HSSZPTVPAVZRR45SAY6A6E3U2P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"John Asmuth, Michael L. Littman","submitted_at":"2012-02-14T16:41:17Z","abstract_excerpt":"Bayes-optimal behavior, while well-defined, is often difficult to achieve. Recent advances in the use of Monte-Carlo tree search (MCTS) have shown that it is possible to act near-optimally in Markov Decision Processes (MDPs) with very large or infinite state spaces. Bayes-optimal behavior in an unknown MDP is equivalent to optimal behavior in the known belief-space MDP, although the size of this belief-space MDP grows exponentially with the amount of history retained, and is potentially infinite. We show how an agent can use one particular MCTS algorithm, Forward Search Sparse Sampling (FSSS),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3699","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":"2026-05-18T04:02:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vllZrjNQOguHJZ2mgK7tnELb7cB5EJ0mldtjnbw8Ra37leP1Bzsk6nJoBSElrLOuGIjVbtsJF407vxiJhhmrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T14:27:53.191033Z"},"content_sha256":"7be2f52069ba26d3a735d578c5ac8a7dd88d3a8f543aa990ca6184ae59962b1c","schema_version":"1.0","event_id":"sha256:7be2f52069ba26d3a735d578c5ac8a7dd88d3a8f543aa990ca6184ae59962b1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/bundle.json","state_url":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/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":"2026-06-28T14:27:53Z","links":{"resolver":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P","bundle":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/bundle.json","state":"https://pith.science/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HSSZPTVPAVZRR45SAY6A6E3U2P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:HSSZPTVPAVZRR45SAY6A6E3U2P","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":"e3537fdf202976c8fe777234f8448121f5fbb8ab5edf24c7023b1f8dd26ee30c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","title_canon_sha256":"0cb1178f66869cc9bdf9f57cc67d3032fa3ec16b6d612ea6fcf8644a26a4e23e"},"schema_version":"1.0","source":{"id":"1202.3699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.3699","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"arxiv_version","alias_value":"1202.3699v1","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3699","created_at":"2026-05-18T04:02:03Z"},{"alias_kind":"pith_short_12","alias_value":"HSSZPTVPAVZR","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"HSSZPTVPAVZRR45S","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"HSSZPTVP","created_at":"2026-05-18T12:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:7be2f52069ba26d3a735d578c5ac8a7dd88d3a8f543aa990ca6184ae59962b1c","target":"graph","created_at":"2026-05-18T04:02:03Z","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":"Bayes-optimal behavior, while well-defined, is often difficult to achieve. Recent advances in the use of Monte-Carlo tree search (MCTS) have shown that it is possible to act near-optimally in Markov Decision Processes (MDPs) with very large or infinite state spaces. Bayes-optimal behavior in an unknown MDP is equivalent to optimal behavior in the known belief-space MDP, although the size of this belief-space MDP grows exponentially with the amount of history retained, and is potentially infinite. We show how an agent can use one particular MCTS algorithm, Forward Search Sparse Sampling (FSSS),","authors_text":"John Asmuth, Michael L. Littman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","title":"Learning is planning: near Bayes-optimal reinforcement learning via Monte-Carlo tree search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3699","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:bf0c8fabb4230c68dcda92c060e7bfc36aa6a8424c30b37dcc20bd99d503c585","target":"record","created_at":"2026-05-18T04:02:03Z","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":"e3537fdf202976c8fe777234f8448121f5fbb8ab5edf24c7023b1f8dd26ee30c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-02-14T16:41:17Z","title_canon_sha256":"0cb1178f66869cc9bdf9f57cc67d3032fa3ec16b6d612ea6fcf8644a26a4e23e"},"schema_version":"1.0","source":{"id":"1202.3699","kind":"arxiv","version":1}},"canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ca597ceaf057318f3b2063c0f1374d3fa713801fcf00d06b80ab90daed9a347","first_computed_at":"2026-05-18T04:02:03.521556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:02:03.521556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RK0LRkrmEz+twuaidVGdDlb/AURQbGUw2V+j7K/phfnp3Yw4LPyPoRfS337xWspMKD76kHeCslA6UkRhUF1qCA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:02:03.522164Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.3699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf0c8fabb4230c68dcda92c060e7bfc36aa6a8424c30b37dcc20bd99d503c585","sha256:7be2f52069ba26d3a735d578c5ac8a7dd88d3a8f543aa990ca6184ae59962b1c"],"state_sha256":"8fb6ae42ed80ee2d1992c507f0de3a69502b877b72439c42b92bfa6308aa69e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F/xUkJwlUJq5TzLFsm7eiX9PCqa40IjCm/NLl6wsy4BCuuntgEUJxFrOrvZkPx/HGjhkDbKLwIpf25Bmdq9BDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T14:27:53.192875Z","bundle_sha256":"8e15473aebc3d4a7ef26e28f6ffcdcb5c5696f065bd666b025532032a727d6cc"}}