{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YY5BJV2J7KYWO2EB5PKYGGGDIK","short_pith_number":"pith:YY5BJV2J","canonical_record":{"source":{"id":"2410.06508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T03:20:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"082bdd7d31a7e94f2108a745314fd51334152391931d035d9147017c01b7a7bb","abstract_canon_sha256":"ad83494e22b597ee8216b282e879679af86c3ab194f65b03a273f59260ff3a46"},"schema_version":"1.0"},"canonical_sha256":"c63a14d749fab1676881ebd58318c3428fc9799d8bf8a14410dce614a604046d","source":{"kind":"arxiv","id":"2410.06508","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06508","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06508v1","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06508","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"YY5BJV2J7KYW","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"YY5BJV2J7KYWO2EB","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"YY5BJV2J","created_at":"2026-07-05T09:18:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YY5BJV2J7KYWO2EB5PKYGGGDIK","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T03:20:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"082bdd7d31a7e94f2108a745314fd51334152391931d035d9147017c01b7a7bb","abstract_canon_sha256":"ad83494e22b597ee8216b282e879679af86c3ab194f65b03a273f59260ff3a46"},"schema_version":"1.0"},"canonical_sha256":"c63a14d749fab1676881ebd58318c3428fc9799d8bf8a14410dce614a604046d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:02.825410Z","signature_b64":"MAP3RhBIcHY31q1F2JacucieFvT21TSe55DAfNyA81+5Sncets5fI5TE+yyL4S92NFh1zjvOQssh1tzeENpBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c63a14d749fab1676881ebd58318c3428fc9799d8bf8a14410dce614a604046d","last_reissued_at":"2026-07-05T09:18:02.824915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:02.824915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06508","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":"2026-07-05T09:18:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/TD2MAw3oFkHsZhpgaZPx3VxeJk68SgVZDSM/B0ghRRmOUUI709LKROJKQ8lAqu4vf/VZqPGgRK+kUwctm+kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:46:12.800265Z"},"content_sha256":"dcaa6f02c4230f097a94049aa848a9a1c1ec630fc2e694402031fe7990830273","schema_version":"1.0","event_id":"sha256:dcaa6f02c4230f097a94049aa848a9a1c1ec630fc2e694402031fe7990830273"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YY5BJV2J7KYWO2EB5PKYGGGDIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Baolin Peng, Dian Yu, Dong Yu, Furong Huang, Haitao Mi, Linfeng Song, Xiyao Wang, Ye Tian","submitted_at":"2024-10-09T03:20:02Z","abstract_excerpt":"Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs. Techniques such as SFT or DPO have enabled LLMs to distill high-quality behaviors from MCTS, improving their reasoning performance. However, existing distillation methods underutilize the rich trajectory information generated by MCTS, limiting the potential for improvements in LLM reasoning. In this paper, we propose AlphaLLM-CPL, a novel pairwise training framework that enables LLMs to self-improve through MCTS behavior distillation. AlphaLLM-CPL efficiently leverages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06508","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.06508/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":"2026-07-05T09:18:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+bB0tjLzpCSX9ll6OwwKU/k4Z1NXpQJS60E4Ece8ew6GzlJalt7QiMWR+rECOD59f3IoSVyGj9mXSN/Wi/KZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:46:12.801181Z"},"content_sha256":"3420ddf53bf49911f49dc579f10efd1c4617b684bff4e476b5c9fe37bf3b253d","schema_version":"1.0","event_id":"sha256:3420ddf53bf49911f49dc579f10efd1c4617b684bff4e476b5c9fe37bf3b253d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YY5BJV2J7KYWO2EB5PKYGGGDIK/bundle.json","state_url":"https://pith.science/pith/YY5BJV2J7KYWO2EB5PKYGGGDIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YY5BJV2J7KYWO2EB5PKYGGGDIK/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":"2026-08-04T23:46:12Z","links":{"resolver":"https://pith.science/pith/YY5BJV2J7KYWO2EB5PKYGGGDIK","bundle":"https://pith.science/pith/YY5BJV2J7KYWO2EB5PKYGGGDIK/bundle.json","state":"https://pith.science/pith/YY5BJV2J7KYWO2EB5PKYGGGDIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YY5BJV2J7KYWO2EB5PKYGGGDIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YY5BJV2J7KYWO2EB5PKYGGGDIK","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":"ad83494e22b597ee8216b282e879679af86c3ab194f65b03a273f59260ff3a46","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T03:20:02Z","title_canon_sha256":"082bdd7d31a7e94f2108a745314fd51334152391931d035d9147017c01b7a7bb"},"schema_version":"1.0","source":{"id":"2410.06508","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06508","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06508v1","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06508","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"YY5BJV2J7KYW","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"YY5BJV2J7KYWO2EB","created_at":"2026-07-05T09:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"YY5BJV2J","created_at":"2026-07-05T09:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:3420ddf53bf49911f49dc579f10efd1c4617b684bff4e476b5c9fe37bf3b253d","target":"graph","created_at":"2026-07-05T09:18:02Z","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/2410.06508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs. Techniques such as SFT or DPO have enabled LLMs to distill high-quality behaviors from MCTS, improving their reasoning performance. However, existing distillation methods underutilize the rich trajectory information generated by MCTS, limiting the potential for improvements in LLM reasoning. In this paper, we propose AlphaLLM-CPL, a novel pairwise training framework that enables LLMs to self-improve through MCTS behavior distillation. AlphaLLM-CPL efficiently leverages ","authors_text":"Baolin Peng, Dian Yu, Dong Yu, Furong Huang, Haitao Mi, Linfeng Song, Xiyao Wang, Ye Tian","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T03:20:02Z","title":"Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06508","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:dcaa6f02c4230f097a94049aa848a9a1c1ec630fc2e694402031fe7990830273","target":"record","created_at":"2026-07-05T09:18:02Z","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":"ad83494e22b597ee8216b282e879679af86c3ab194f65b03a273f59260ff3a46","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T03:20:02Z","title_canon_sha256":"082bdd7d31a7e94f2108a745314fd51334152391931d035d9147017c01b7a7bb"},"schema_version":"1.0","source":{"id":"2410.06508","kind":"arxiv","version":1}},"canonical_sha256":"c63a14d749fab1676881ebd58318c3428fc9799d8bf8a14410dce614a604046d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c63a14d749fab1676881ebd58318c3428fc9799d8bf8a14410dce614a604046d","first_computed_at":"2026-07-05T09:18:02.824915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:02.824915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MAP3RhBIcHY31q1F2JacucieFvT21TSe55DAfNyA81+5Sncets5fI5TE+yyL4S92NFh1zjvOQssh1tzeENpBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:02.825410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06508","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcaa6f02c4230f097a94049aa848a9a1c1ec630fc2e694402031fe7990830273","sha256:3420ddf53bf49911f49dc579f10efd1c4617b684bff4e476b5c9fe37bf3b253d"],"state_sha256":"8adeed46609b4885e431d8afb97083755c1e7be975713de210e7e0a640f5e239"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWsttlEIQx9CiZHX/fP+gJoxlY4fH2DqvkO7am8GMmJQ5WqWFmORwImhdrt+Cf6jK72PbkhTnHvIIHYY+L0IAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:46:12.807440Z","bundle_sha256":"25f50f311a4ec683bdc58ee9cd1560e4359cc686a0f90a2eae8b1fd5ccbf4c16"}}