{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:POOJJLSQUD7X6RYSAEEEIG3WCQ","short_pith_number":"pith:POOJJLSQ","canonical_record":{"source":{"id":"1206.5940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-26T09:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"f42a9d5c21298f6ebb0b9dfbc47a34f973570af362b6bbd21ae561fe9682d050","abstract_canon_sha256":"a1a5c22baf5a0d66e54c1b461508fbd9d40f8ffc55c231281be1b6a41addaa66"},"schema_version":"1.0"},"canonical_sha256":"7b9c94ae50a0ff7f47120108441b76143111c8c65f426ad362554973e540e14a","source":{"kind":"arxiv","id":"1206.5940","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5940","created_at":"2026-05-18T03:52:37Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5940v1","created_at":"2026-05-18T03:52:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5940","created_at":"2026-05-18T03:52:37Z"},{"alias_kind":"pith_short_12","alias_value":"POOJJLSQUD7X","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"POOJJLSQUD7X6RYS","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"POOJJLSQ","created_at":"2026-05-18T12:27:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:POOJJLSQUD7X6RYSAEEEIG3WCQ","target":"record","payload":{"canonical_record":{"source":{"id":"1206.5940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-26T09:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"f42a9d5c21298f6ebb0b9dfbc47a34f973570af362b6bbd21ae561fe9682d050","abstract_canon_sha256":"a1a5c22baf5a0d66e54c1b461508fbd9d40f8ffc55c231281be1b6a41addaa66"},"schema_version":"1.0"},"canonical_sha256":"7b9c94ae50a0ff7f47120108441b76143111c8c65f426ad362554973e540e14a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:37.585122Z","signature_b64":"jsYZ7n9tnLZihj7oav0Zcg5Ga4GP1QrjOlQSRHOGpKSKaGdmxvfwjxQI09r984OCUqLgyiPMjljv6Q7OgVqtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b9c94ae50a0ff7f47120108441b76143111c8c65f426ad362554973e540e14a","last_reissued_at":"2026-05-18T03:52:37.584422Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:37.584422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.5940","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":"2026-05-18T03:52:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e2iCI4FKfYZoXXw5r3vy2M+biXKOEK4ofXA8ce2+/OoA2dWiiVsaRFk2o98NKZF96qMmKqp22za0Skw1EauzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:08:02.449219Z"},"content_sha256":"2e21c8268da0c533bec263de9d25a166d54712ab6be6e4bd8ea94e995bd84e11","schema_version":"1.0","event_id":"sha256:2e21c8268da0c533bec263de9d25a166d54712ab6be6e4bd8ea94e995bd84e11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:POOJJLSQUD7X6RYSAEEEIG3WCQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bootstrapping Monte Carlo Tree Search with an Imperfect Heuristic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Truong-Huy Dinh Nguyen, Tze-Yun Leong, Wee-Sun Lee","submitted_at":"2012-06-26T09:53:59Z","abstract_excerpt":"We consider the problem of using a heuristic policy to improve the value approximation by the Upper Confidence Bound applied in Trees (UCT) algorithm in non-adversarial settings such as planning with large-state space Markov Decision Processes. Current improvements to UCT focus on either changing the action selection formula at the internal nodes or the rollout policy at the leaf nodes of the search tree. In this work, we propose to add an auxiliary arm to each of the internal nodes, and always use the heuristic policy to roll out simulations at the auxiliary arms. The method aims to get fast "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5940","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":"2026-05-18T03:52:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Ua+lRXhL54a/PU7xkPdY6VOFG7VIGm+86X7bX/TQOsDKVHzu/A/z3CCeKMwSJ5fQnnb6LwLV5bi7iW1cfS8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:08:02.449618Z"},"content_sha256":"46638fef129b01914b88928b16232d152875247331f32121d30273f8380b4c34","schema_version":"1.0","event_id":"sha256:46638fef129b01914b88928b16232d152875247331f32121d30273f8380b4c34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POOJJLSQUD7X6RYSAEEEIG3WCQ/bundle.json","state_url":"https://pith.science/pith/POOJJLSQUD7X6RYSAEEEIG3WCQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POOJJLSQUD7X6RYSAEEEIG3WCQ/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":"2026-06-07T16:08:02Z","links":{"resolver":"https://pith.science/pith/POOJJLSQUD7X6RYSAEEEIG3WCQ","bundle":"https://pith.science/pith/POOJJLSQUD7X6RYSAEEEIG3WCQ/bundle.json","state":"https://pith.science/pith/POOJJLSQUD7X6RYSAEEEIG3WCQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POOJJLSQUD7X6RYSAEEEIG3WCQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:POOJJLSQUD7X6RYSAEEEIG3WCQ","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":"a1a5c22baf5a0d66e54c1b461508fbd9d40f8ffc55c231281be1b6a41addaa66","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-26T09:53:59Z","title_canon_sha256":"f42a9d5c21298f6ebb0b9dfbc47a34f973570af362b6bbd21ae561fe9682d050"},"schema_version":"1.0","source":{"id":"1206.5940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5940","created_at":"2026-05-18T03:52:37Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5940v1","created_at":"2026-05-18T03:52:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5940","created_at":"2026-05-18T03:52:37Z"},{"alias_kind":"pith_short_12","alias_value":"POOJJLSQUD7X","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"POOJJLSQUD7X6RYS","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"POOJJLSQ","created_at":"2026-05-18T12:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:46638fef129b01914b88928b16232d152875247331f32121d30273f8380b4c34","target":"graph","created_at":"2026-05-18T03:52:37Z","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":"We consider the problem of using a heuristic policy to improve the value approximation by the Upper Confidence Bound applied in Trees (UCT) algorithm in non-adversarial settings such as planning with large-state space Markov Decision Processes. Current improvements to UCT focus on either changing the action selection formula at the internal nodes or the rollout policy at the leaf nodes of the search tree. In this work, we propose to add an auxiliary arm to each of the internal nodes, and always use the heuristic policy to roll out simulations at the auxiliary arms. The method aims to get fast ","authors_text":"Truong-Huy Dinh Nguyen, Tze-Yun Leong, Wee-Sun Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-26T09:53:59Z","title":"Bootstrapping Monte Carlo Tree Search with an Imperfect Heuristic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5940","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":"sha256:2e21c8268da0c533bec263de9d25a166d54712ab6be6e4bd8ea94e995bd84e11","target":"record","created_at":"2026-05-18T03:52:37Z","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":"a1a5c22baf5a0d66e54c1b461508fbd9d40f8ffc55c231281be1b6a41addaa66","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-26T09:53:59Z","title_canon_sha256":"f42a9d5c21298f6ebb0b9dfbc47a34f973570af362b6bbd21ae561fe9682d050"},"schema_version":"1.0","source":{"id":"1206.5940","kind":"arxiv","version":1}},"canonical_sha256":"7b9c94ae50a0ff7f47120108441b76143111c8c65f426ad362554973e540e14a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b9c94ae50a0ff7f47120108441b76143111c8c65f426ad362554973e540e14a","first_computed_at":"2026-05-18T03:52:37.584422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:37.584422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jsYZ7n9tnLZihj7oav0Zcg5Ga4GP1QrjOlQSRHOGpKSKaGdmxvfwjxQI09r984OCUqLgyiPMjljv6Q7OgVqtAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:37.585122Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.5940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e21c8268da0c533bec263de9d25a166d54712ab6be6e4bd8ea94e995bd84e11","sha256:46638fef129b01914b88928b16232d152875247331f32121d30273f8380b4c34"],"state_sha256":"95727a3651a5a69397e4e7dc979aa1fc745f1a0644f3fcaf46aba0475308aaa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M3aY2zysqLI4ttYSe2ePK0JnJ3QmQ+97WCLGf6GpfIif3+eU/h5YZIh9UAkkXWN47wJwvd/4+5E3KJ9pA4aCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T16:08:02.452160Z","bundle_sha256":"23e6b96630e0fa12651458b4691974cca2ca3cfc8a212a77688d411def62a3b3"}}