{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QHDATL6PRPHOOQEJOJXIAGEP2R","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":"09d139f3b9f099fa0afcab3c9365bb0c8f1a88174f9455665dfd43170a5e94f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T07:40:00Z","title_canon_sha256":"e0193e56630e62ecefc5e26869b0d34823cf01b3f95d8167785825e3404eb6e0"},"schema_version":"1.0","source":{"id":"2406.03816","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03816","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03816v3","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03816","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_12","alias_value":"QHDATL6PRPHO","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_16","alias_value":"QHDATL6PRPHOOQEJ","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_8","alias_value":"QHDATL6P","created_at":"2026-07-05T09:36:41Z"}],"graph_snapshots":[{"event_id":"sha256:bd8bbeddaeb4b226f1f5191e558f4c9ae712a60f6d684c22b79c00f2aa2bac4e","target":"graph","created_at":"2026-07-05T09:36:41Z","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/2406.03816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or intermediate reasoning). In this paper, we develop a reinforced self-training approach, called ReST-MCTS*, based on integrating process reward guidance with tree search MCTS* for collecting higher-quality reasoning traces as well as per-step value to train policy and reward models. ReST-MCTS* circumvents the per-step manual annotation typically used to train","authors_text":"Dan Zhang, Jie Tang, Sining Zhoubian, Yisong Yue, Yuxiao Dong, Ziniu Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T07:40:00Z","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03816","kind":"arxiv","version":3},"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":"sha256:5a77bcba4fe6f56b09aa5130874a5c854e4ee16a89b27934dad3696087c364a2","target":"record","created_at":"2026-07-05T09:36:41Z","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":"09d139f3b9f099fa0afcab3c9365bb0c8f1a88174f9455665dfd43170a5e94f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T07:40:00Z","title_canon_sha256":"e0193e56630e62ecefc5e26869b0d34823cf01b3f95d8167785825e3404eb6e0"},"schema_version":"1.0","source":{"id":"2406.03816","kind":"arxiv","version":3}},"canonical_sha256":"81c609afcf8bcee74089726e80188fd45b420521cc68725ab2c7477629df50a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81c609afcf8bcee74089726e80188fd45b420521cc68725ab2c7477629df50a1","first_computed_at":"2026-07-05T09:36:41.361420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:41.361420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O0eabWi+CZi5Z+yZEH3a+TnpbWhRwZx+/VOg9MJ9z/FlboD6Om29ST/+9kvLdKdseqKUx+AiNmNTtnMEPFPcDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:41.361910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03816","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a77bcba4fe6f56b09aa5130874a5c854e4ee16a89b27934dad3696087c364a2","sha256:bd8bbeddaeb4b226f1f5191e558f4c9ae712a60f6d684c22b79c00f2aa2bac4e"],"state_sha256":"ef6c4d839230e84c2778621af1e9cea36cf450371c3b29c19a74e02dd5ab1a38"}