{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:72EFKVXW5C6ICUKWCFFKEYS37N","short_pith_number":"pith:72EFKVXW","schema_version":"1.0","canonical_sha256":"fe885556f6e8bc815156114aa2625bfb636ba5c71274f6113826fc8827f7ff32","source":{"kind":"arxiv","id":"2505.12031","version":1},"attestation_state":"computed","paper":{"title":"LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chun Cao, Jiakun Zhang, Jiarui Zhang, Jingwei Xu, Junyu Lai, Shuo Xu, Taolue Chen, Yao Yang, Zihang Wang","submitted_at":"2025-05-17T14:47:36Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have sparked considerable interest in automated theorem proving and a prominent line of research integrates stepwise LLM-based provers into tree search. In this paper, we introduce a novel proof-state exploration approach for training data synthesis, designed to produce diverse tactics across a wide range of intermediate proof states, thereby facilitating effective one-shot fine-tuning of LLM as the policy model. We also propose an adaptive beam size strategy, which effectively takes advantage of our data synthesis method and achieves a trade"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.12031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T14:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"e09cbf602ebd29257553f39f2fb2e1fdb0b5bd50f419dcb58c93cc60a3ed58b8","abstract_canon_sha256":"cb42032ea85273fc39737d17e140dfad283a7d4b4775c96d3c322a74e3494be8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:57.180938Z","signature_b64":"WV9HGF8J1xHTUT/77oM07AjD/Xh8ihbWTR34p1er4qWSP23gZotXg0EaaHkCzVjen/yl7Ofw3oux1teVQDafBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe885556f6e8bc815156114aa2625bfb636ba5c71274f6113826fc8827f7ff32","last_reissued_at":"2026-07-05T11:04:57.180421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:57.180421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chun Cao, Jiakun Zhang, Jiarui Zhang, Jingwei Xu, Junyu Lai, Shuo Xu, Taolue Chen, Yao Yang, Zihang Wang","submitted_at":"2025-05-17T14:47:36Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have sparked considerable interest in automated theorem proving and a prominent line of research integrates stepwise LLM-based provers into tree search. In this paper, we introduce a novel proof-state exploration approach for training data synthesis, designed to produce diverse tactics across a wide range of intermediate proof states, thereby facilitating effective one-shot fine-tuning of LLM as the policy model. We also propose an adaptive beam size strategy, which effectively takes advantage of our data synthesis method and achieves a trade"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12031","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/2505.12031/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.12031","created_at":"2026-07-05T11:04:57.180490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12031v1","created_at":"2026-07-05T11:04:57.180490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12031","created_at":"2026-07-05T11:04:57.180490+00:00"},{"alias_kind":"pith_short_12","alias_value":"72EFKVXW5C6I","created_at":"2026-07-05T11:04:57.180490+00:00"},{"alias_kind":"pith_short_16","alias_value":"72EFKVXW5C6ICUKW","created_at":"2026-07-05T11:04:57.180490+00:00"},{"alias_kind":"pith_short_8","alias_value":"72EFKVXW","created_at":"2026-07-05T11:04:57.180490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.21220","citing_title":"Search Hardness-Aware LLM-Based Problem Formulation for Expensive Simulation-Driven Design","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N","json":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N.json","graph_json":"https://pith.science/api/pith-number/72EFKVXW5C6ICUKWCFFKEYS37N/graph.json","events_json":"https://pith.science/api/pith-number/72EFKVXW5C6ICUKWCFFKEYS37N/events.json","paper":"https://pith.science/paper/72EFKVXW"},"agent_actions":{"view_html":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N","download_json":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N.json","view_paper":"https://pith.science/paper/72EFKVXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12031&json=true","fetch_graph":"https://pith.science/api/pith-number/72EFKVXW5C6ICUKWCFFKEYS37N/graph.json","fetch_events":"https://pith.science/api/pith-number/72EFKVXW5C6ICUKWCFFKEYS37N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/action/storage_attestation","attest_author":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/action/author_attestation","sign_citation":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/action/citation_signature","submit_replication":"https://pith.science/pith/72EFKVXW5C6ICUKWCFFKEYS37N/action/replication_record"}},"created_at":"2026-07-05T11:04:57.180490+00:00","updated_at":"2026-07-05T11:04:57.180490+00:00"}