{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EXHOAWT5XR4YMAEWCLZFADDXWN","short_pith_number":"pith:EXHOAWT5","schema_version":"1.0","canonical_sha256":"25cee05a7dbc7986009612f2500c77b34bf0dd62d87e919fbc91d5739c305ac0","source":{"kind":"arxiv","id":"2402.08957","version":3},"attestation_state":"computed","paper":{"title":"MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.FL","cs.LG","cs.PL"],"primary_cat":"cs.AI","authors_text":"Haiming Wang, Huajian Xin, Linqi Song, Qingxing Cao, Xiaodan Liang, Xiaohan Lin, Yinya Huang, Zhenguo Li, Zhengying Liu","submitted_at":"2024-02-14T05:57:58Z","abstract_excerpt":"Recent large language models (LLMs) have witnessed significant advancement in various tasks, including mathematical reasoning and theorem proving. As these two tasks require strict and formal multi-step inference, they are appealing domains for exploring the reasoning ability of LLMs but still face important challenges. Previous studies such as Chain-of-Thought (CoT) have revealed the effectiveness of intermediate steps guidance. However, such step-wise annotation requires heavy labor, leading to insufficient training steps for current benchmarks. To fill this gap, this work introduces MUSTARD"},"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":"2402.08957","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T05:57:58Z","cross_cats_sorted":["cs.CL","cs.FL","cs.LG","cs.PL"],"title_canon_sha256":"b428b07db72b4c25260d5740a7be5b050a55bfd9b52a2cfb4df57b9d7f387b51","abstract_canon_sha256":"f1c88c7e9de33dda49ff4884a8e6db0ea2590445c3a3c14cdd8f2c61f1517a47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:50.081724Z","signature_b64":"Eueg0mXGNu5MgHc0zc4Y7qdLSWwckHuWZzrrlUcAzCTrEm0glW91m77XtXO2obLBPQLd50gJCYhZWU38awgBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25cee05a7dbc7986009612f2500c77b34bf0dd62d87e919fbc91d5739c305ac0","last_reissued_at":"2026-07-05T08:21:50.081232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:50.081232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.FL","cs.LG","cs.PL"],"primary_cat":"cs.AI","authors_text":"Haiming Wang, Huajian Xin, Linqi Song, Qingxing Cao, Xiaodan Liang, Xiaohan Lin, Yinya Huang, Zhenguo Li, Zhengying Liu","submitted_at":"2024-02-14T05:57:58Z","abstract_excerpt":"Recent large language models (LLMs) have witnessed significant advancement in various tasks, including mathematical reasoning and theorem proving. As these two tasks require strict and formal multi-step inference, they are appealing domains for exploring the reasoning ability of LLMs but still face important challenges. Previous studies such as Chain-of-Thought (CoT) have revealed the effectiveness of intermediate steps guidance. However, such step-wise annotation requires heavy labor, leading to insufficient training steps for current benchmarks. To fill this gap, this work introduces MUSTARD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08957","kind":"arxiv","version":3},"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/2402.08957/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":"2402.08957","created_at":"2026-07-05T08:21:50.081289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08957v3","created_at":"2026-07-05T08:21:50.081289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08957","created_at":"2026-07-05T08:21:50.081289+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXHOAWT5XR4Y","created_at":"2026-07-05T08:21:50.081289+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXHOAWT5XR4YMAEW","created_at":"2026-07-05T08:21:50.081289+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXHOAWT5","created_at":"2026-07-05T08:21:50.081289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01008","citing_title":"FVSpec: Real-World Property-Based Tests as Lean Challenges","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN","json":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN.json","graph_json":"https://pith.science/api/pith-number/EXHOAWT5XR4YMAEWCLZFADDXWN/graph.json","events_json":"https://pith.science/api/pith-number/EXHOAWT5XR4YMAEWCLZFADDXWN/events.json","paper":"https://pith.science/paper/EXHOAWT5"},"agent_actions":{"view_html":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN","download_json":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN.json","view_paper":"https://pith.science/paper/EXHOAWT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08957&json=true","fetch_graph":"https://pith.science/api/pith-number/EXHOAWT5XR4YMAEWCLZFADDXWN/graph.json","fetch_events":"https://pith.science/api/pith-number/EXHOAWT5XR4YMAEWCLZFADDXWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN/action/storage_attestation","attest_author":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN/action/author_attestation","sign_citation":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN/action/citation_signature","submit_replication":"https://pith.science/pith/EXHOAWT5XR4YMAEWCLZFADDXWN/action/replication_record"}},"created_at":"2026-07-05T08:21:50.081289+00:00","updated_at":"2026-07-05T08:21:50.081289+00:00"}