{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VL5O74ICDVJNMAXR7BSO4BH5K2","short_pith_number":"pith:VL5O74IC","canonical_record":{"source":{"id":"2405.00451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-01T11:10:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12c09afcab6ead52f8af2a4a107bc5592ef43c6cc98cffe3e10e8ce1cd8f83f3","abstract_canon_sha256":"0a0acfb0680fc60973fb1913fd32dec6b8306ec63f770cf38d56b8641aeb451e"},"schema_version":"1.0"},"canonical_sha256":"aafaeff1021d52d602f1f864ee04fd5692fb36a6f0d149dc3c00e17c5ab80b46","source":{"kind":"arxiv","id":"2405.00451","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00451","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00451v2","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00451","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"pith_short_12","alias_value":"VL5O74ICDVJN","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"VL5O74ICDVJNMAXR","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"VL5O74IC","created_at":"2026-07-05T08:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VL5O74ICDVJNMAXR7BSO4BH5K2","target":"record","payload":{"canonical_record":{"source":{"id":"2405.00451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-01T11:10:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12c09afcab6ead52f8af2a4a107bc5592ef43c6cc98cffe3e10e8ce1cd8f83f3","abstract_canon_sha256":"0a0acfb0680fc60973fb1913fd32dec6b8306ec63f770cf38d56b8641aeb451e"},"schema_version":"1.0"},"canonical_sha256":"aafaeff1021d52d602f1f864ee04fd5692fb36a6f0d149dc3c00e17c5ab80b46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:01.840679Z","signature_b64":"Rcb9dszi9xbmSkO+T5rw5uFhsLrQzHxBmq1Prr9e9pQhKlFPopr0kK7MlS7R6mRxNV2hkuq6mUIi+LGfBYCqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aafaeff1021d52d602f1f864ee04fd5692fb36a6f0d149dc3c00e17c5ab80b46","last_reissued_at":"2026-07-05T08:33:01.840151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:01.840151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.00451","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:33:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"seVA4wcwVr1dreBpD1uKgggHX4B/WOXCyMleCDgV1WDzqqh2ad4mOriYbrkD+TLFkyNZDWlsD1kh7eE/9hobBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:22:58.782714Z"},"content_sha256":"df30be8d93d701344c40c84a33b96798fa336aea337b6401bcbca110b75e32fb","schema_version":"1.0","event_id":"sha256:df30be8d93d701344c40c84a33b96798fa336aea337b6401bcbca110b75e32fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VL5O74ICDVJNMAXR7BSO4BH5K2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Anirudh Goyal, Kenji Kawaguchi, Michael Shieh, Min-Yen Kan, Timothy P. Lillicrap, Wenyue Zheng, Yuxi Xie","submitted_at":"2024-05-01T11:10:24Z","abstract_excerpt":"We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process inspired by the successful strategy employed by AlphaZero. Our work leverages Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. To enhance consistency in intermediate steps, we combine outcome validation and stepwise self-evaluation, continually updating the quality assessment of newly generated data. The proposed al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00451","kind":"arxiv","version":2},"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/2405.00451/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":"2026-07-05T08:33:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+LKDodIswzl0vxvqmsRec7uWkv3vHty16B/3QQhe/sy/WIygXU6gIMZ4hnQz1RNd1COsn209H4olCNX0pkYhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:22:58.783431Z"},"content_sha256":"2a6129305e5b0813fc46b1dc6790ab5e2c1df76d24e264699611f4ea8486c790","schema_version":"1.0","event_id":"sha256:2a6129305e5b0813fc46b1dc6790ab5e2c1df76d24e264699611f4ea8486c790"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VL5O74ICDVJNMAXR7BSO4BH5K2/bundle.json","state_url":"https://pith.science/pith/VL5O74ICDVJNMAXR7BSO4BH5K2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VL5O74ICDVJNMAXR7BSO4BH5K2/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":"2026-08-03T18:22:58Z","links":{"resolver":"https://pith.science/pith/VL5O74ICDVJNMAXR7BSO4BH5K2","bundle":"https://pith.science/pith/VL5O74ICDVJNMAXR7BSO4BH5K2/bundle.json","state":"https://pith.science/pith/VL5O74ICDVJNMAXR7BSO4BH5K2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VL5O74ICDVJNMAXR7BSO4BH5K2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VL5O74ICDVJNMAXR7BSO4BH5K2","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":"0a0acfb0680fc60973fb1913fd32dec6b8306ec63f770cf38d56b8641aeb451e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-01T11:10:24Z","title_canon_sha256":"12c09afcab6ead52f8af2a4a107bc5592ef43c6cc98cffe3e10e8ce1cd8f83f3"},"schema_version":"1.0","source":{"id":"2405.00451","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00451","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00451v2","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00451","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"pith_short_12","alias_value":"VL5O74ICDVJN","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"VL5O74ICDVJNMAXR","created_at":"2026-07-05T08:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"VL5O74IC","created_at":"2026-07-05T08:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:2a6129305e5b0813fc46b1dc6790ab5e2c1df76d24e264699611f4ea8486c790","target":"graph","created_at":"2026-07-05T08:33:01Z","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/2405.00451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process inspired by the successful strategy employed by AlphaZero. Our work leverages Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. To enhance consistency in intermediate steps, we combine outcome validation and stepwise self-evaluation, continually updating the quality assessment of newly generated data. The proposed al","authors_text":"Anirudh Goyal, Kenji Kawaguchi, Michael Shieh, Min-Yen Kan, Timothy P. Lillicrap, Wenyue Zheng, Yuxi Xie","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-01T11:10:24Z","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00451","kind":"arxiv","version":2},"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:df30be8d93d701344c40c84a33b96798fa336aea337b6401bcbca110b75e32fb","target":"record","created_at":"2026-07-05T08:33:01Z","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":"0a0acfb0680fc60973fb1913fd32dec6b8306ec63f770cf38d56b8641aeb451e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-01T11:10:24Z","title_canon_sha256":"12c09afcab6ead52f8af2a4a107bc5592ef43c6cc98cffe3e10e8ce1cd8f83f3"},"schema_version":"1.0","source":{"id":"2405.00451","kind":"arxiv","version":2}},"canonical_sha256":"aafaeff1021d52d602f1f864ee04fd5692fb36a6f0d149dc3c00e17c5ab80b46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aafaeff1021d52d602f1f864ee04fd5692fb36a6f0d149dc3c00e17c5ab80b46","first_computed_at":"2026-07-05T08:33:01.840151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:01.840151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rcb9dszi9xbmSkO+T5rw5uFhsLrQzHxBmq1Prr9e9pQhKlFPopr0kK7MlS7R6mRxNV2hkuq6mUIi+LGfBYCqCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:01.840679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00451","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df30be8d93d701344c40c84a33b96798fa336aea337b6401bcbca110b75e32fb","sha256:2a6129305e5b0813fc46b1dc6790ab5e2c1df76d24e264699611f4ea8486c790"],"state_sha256":"2707fca71c3bd1828c42a34b94de942056c16c20690d1a367d793c67e55ada89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"idi++cSIW7dIMEQx1YRReY9zhrAouKB6B8jMEgrHX5RuNBSYVMCtOfyNsO4w5iLhCxJvmi/EkcynHbyNJi/yBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:22:58.791579Z","bundle_sha256":"cad42c26f05576240172c3b9ea9a006b2c1b9ffa0f03bf20cbbf57188d99d66f"}}