{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZLDIFVCE5L7K3T5DLSWSPHGKPY","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":"82ab060f96a357f36dba7338071dab1efb58065f8b576e613279dabaa82e228f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T14:12:57Z","title_canon_sha256":"2fbcdee4b0e850ff9f844008d3b960df9e2f2ad5a5c20fa8623f24b32d173b53"},"schema_version":"1.0","source":{"id":"2501.04519","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04519","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04519v1","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04519","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZLDIFVCE5L7K","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZLDIFVCE5L7K3T5D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZLDIFVCE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:93921391e35923ad158090daf2a9e05632ba4c129f40f0c1a283b0aa78e0714e","target":"graph","created_at":"2026-05-17T23:38:15Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Through 4 rounds of self-evolution with millions of synthesized solutions for 747k math problems, rStar-Math boosts SLMs' math reasoning to state-of-the-art levels. On the MATH benchmark, it improves Qwen2.5-Math-7B from 58.8% to 90.0% and Phi3-mini-3.8B from 41.4% to 86.4%, surpassing o1-preview by +4.5% and +0.9%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The process preference model trained on self-generated trajectories provides unbiased, accurate step-level guidance during MCTS search and does not overfit to patterns in the synthesized data or the specific benchmarks used for evaluation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Small LLMs reach 90% on the MATH benchmark and solve 53% of AIME problems by self-evolving through MCTS with a process preference model, surpassing o1-preview without distillation from larger models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Small language models reach expert math reasoning by evolving their own search and evaluation processes over repeated rounds."}],"snapshot_sha256":"363770b40a8df31b40ecc59add77611f89c0582ce5628d6b8f95df8052aa63f1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e63b6c453d16ae8b6f6b36b6eb270c5c9a58f4ea36427a2214c3e1996dcc3af6"},"paper":{"abstract_excerpt":"We present rStar-Math to demonstrate that small language models (SLMs) can rival or even surpass the math reasoning capability of OpenAI o1, without distillation from superior models. rStar-Math achieves this by exercising \"deep thinking\" through Monte Carlo Tree Search (MCTS), where a math policy SLM performs test-time search guided by an SLM-based process reward model. rStar-Math introduces three innovations to tackle the challenges in training the two SLMs: (1) a novel code-augmented CoT data sythesis method, which performs extensive MCTS rollouts to generate step-by-step verified reasoning","authors_text":"Fan Yang, Li Lyna Zhang, Mao Yang, Ning Shang, Xinyu Guan, Yifei Liu, Yi Zhu, Youran Sun","cross_cats":[],"headline":"Small language models reach expert math reasoning by evolving their own search and evaluation processes over repeated rounds.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T14:12:57Z","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04519","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-17T04:38:20.584079Z","id":"c06e96ef-f23b-47cd-b08f-5ee9e54e914b","model_set":{"reader":"grok-4.3"},"one_line_summary":"Small LLMs reach 90% on the MATH benchmark and solve 53% of AIME problems by self-evolving through MCTS with a process preference model, surpassing o1-preview without distillation from larger models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Small language models reach expert math reasoning by evolving their own search and evaluation processes over repeated rounds.","strongest_claim":"Through 4 rounds of self-evolution with millions of synthesized solutions for 747k math problems, rStar-Math boosts SLMs' math reasoning to state-of-the-art levels. On the MATH benchmark, it improves Qwen2.5-Math-7B from 58.8% to 90.0% and Phi3-mini-3.8B from 41.4% to 86.4%, surpassing o1-preview by +4.5% and +0.9%.","weakest_assumption":"The process preference model trained on self-generated trajectories provides unbiased, accurate step-level guidance during MCTS search and does not overfit to patterns in the synthesized data or the specific benchmarks used for evaluation."}},"verdict_id":"c06e96ef-f23b-47cd-b08f-5ee9e54e914b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fe48fa3189a2718dc040998448347848ef723d90452b62db428f4d2341be22d8","target":"record","created_at":"2026-05-17T23:38:15Z","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":"82ab060f96a357f36dba7338071dab1efb58065f8b576e613279dabaa82e228f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T14:12:57Z","title_canon_sha256":"2fbcdee4b0e850ff9f844008d3b960df9e2f2ad5a5c20fa8623f24b32d173b53"},"schema_version":"1.0","source":{"id":"2501.04519","kind":"arxiv","version":1}},"canonical_sha256":"cac682d444eafeadcfa35cad279cca7e0fd9d97d688f4665766cae59e4018d90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cac682d444eafeadcfa35cad279cca7e0fd9d97d688f4665766cae59e4018d90","first_computed_at":"2026-05-17T23:38:15.094996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:15.094996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OVZ1c/0i22uabrtoWZqAjY795S0Nthqvka5U16yygAm0cNGcfO9aEebY0OXVfNsfpaER8bQRR5SgH7VxUxYCCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:15.095688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04519","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe48fa3189a2718dc040998448347848ef723d90452b62db428f4d2341be22d8","sha256:93921391e35923ad158090daf2a9e05632ba4c129f40f0c1a283b0aa78e0714e"],"state_sha256":"89c3e2bfe3dcae6cba69af3df9e0bdd9555e17f935bf8803a36c848fad5437f3"}