{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SADCSZHTIQMBRNOQ34CZ4O4SKA","short_pith_number":"pith:SADCSZHT","schema_version":"1.0","canonical_sha256":"90062964f3441818b5d0df059e3b92503d2b7a6ed89343df86ff8074620108ca","source":{"kind":"arxiv","id":"2405.14333","version":1},"attestation_state":"computed","paper":{"title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Liu, Chong Ruan, Daya Guo, Huajian Xin, Qihao Zhu, Wenda Li, Xiaodan Liang, Zhihong Shao, Zhizhou Ren","submitted_at":"2024-05-23T09:03:42Z","abstract_excerpt":"Proof assistants like Lean have revolutionized mathematical proof verification, ensuring high accuracy and reliability. Although large language models (LLMs) show promise in mathematical reasoning, their advancement in formal theorem proving is hindered by a lack of training data. To address this issue, we introduce an approach to generate extensive Lean 4 proof data derived from high-school and undergraduate-level mathematical competition problems. This approach involves translating natural language problems into formal statements, filtering out low-quality statements, and generating proofs t"},"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":"2405.14333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-23T09:03:42Z","cross_cats_sorted":[],"title_canon_sha256":"1dc362adc8492efecd46240742c9dbfb09ac4b251c1785396e03c108e4c66a13","abstract_canon_sha256":"42883e70112878e740c8f8865080cc1b0e59b346e8ca990e42f2a350714e5b8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:13.361923Z","signature_b64":"uymXxnn6tlyWwUzHSPQl3m/AhHFE9JITWGHReCjcbeAG1e+fPB1B4x87RbDVzMEw9BATUEf03qHn2JWWjNC1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90062964f3441818b5d0df059e3b92503d2b7a6ed89343df86ff8074620108ca","last_reissued_at":"2026-07-05T08:22:13.361506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:13.361506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Liu, Chong Ruan, Daya Guo, Huajian Xin, Qihao Zhu, Wenda Li, Xiaodan Liang, Zhihong Shao, Zhizhou Ren","submitted_at":"2024-05-23T09:03:42Z","abstract_excerpt":"Proof assistants like Lean have revolutionized mathematical proof verification, ensuring high accuracy and reliability. Although large language models (LLMs) show promise in mathematical reasoning, their advancement in formal theorem proving is hindered by a lack of training data. To address this issue, we introduce an approach to generate extensive Lean 4 proof data derived from high-school and undergraduate-level mathematical competition problems. This approach involves translating natural language problems into formal statements, filtering out low-quality statements, and generating proofs t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14333","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/2405.14333/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":"2405.14333","created_at":"2026-07-05T08:22:13.361563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14333v1","created_at":"2026-07-05T08:22:13.361563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14333","created_at":"2026-07-05T08:22:13.361563+00:00"},{"alias_kind":"pith_short_12","alias_value":"SADCSZHTIQMB","created_at":"2026-07-05T08:22:13.361563+00:00"},{"alias_kind":"pith_short_16","alias_value":"SADCSZHTIQMBRNOQ","created_at":"2026-07-05T08:22:13.361563+00:00"},{"alias_kind":"pith_short_8","alias_value":"SADCSZHT","created_at":"2026-07-05T08:22:13.361563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24443","citing_title":"Verifiable Auto-Formalization of Mathematics Using a Relaxed Natural Formal Language","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17581","citing_title":"Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31134","citing_title":"Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18098","citing_title":"IsabeLLM: Automated Theorem Proving Applied to Formally Verifying Consensus","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08728","citing_title":"Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01223","citing_title":"Theoria: Rewrite-Acceptability Verification over Informal Reasoning States","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31134","citing_title":"Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28747","citing_title":"Self-Supervised Theorem Discovery in a Formal Axiomatic System","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28841","citing_title":"LAMP: Lean-based Agentic framework with MCP and Proof Repair","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30914","citing_title":"Automating Formal Verification with Reinforcement Learning and Recursive Inference","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12787","citing_title":"Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22875","citing_title":"RMA: an Agentic System for Research-Level Mathematical Problems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":213,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20244","citing_title":"Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20120","citing_title":"Using Aristotle API for AI-Assisted Theorem Proving in Lean 4: A Formalisation Case Study of the Grasshopper Problem","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2406.18629","citing_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13209","citing_title":"AI for Mathematics: Progress, Challenges, and Prospects","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16322","citing_title":"Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2505.24298","citing_title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01346","citing_title":"Aristotle: IMO-level Automated Theorem Proving","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11905","citing_title":"Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08817","citing_title":"How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25155","citing_title":"Rethinking Wireless Communications through Formal Mathematical AI Reasoning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03356","citing_title":"POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA","json":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA.json","graph_json":"https://pith.science/api/pith-number/SADCSZHTIQMBRNOQ34CZ4O4SKA/graph.json","events_json":"https://pith.science/api/pith-number/SADCSZHTIQMBRNOQ34CZ4O4SKA/events.json","paper":"https://pith.science/paper/SADCSZHT"},"agent_actions":{"view_html":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA","download_json":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA.json","view_paper":"https://pith.science/paper/SADCSZHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14333&json=true","fetch_graph":"https://pith.science/api/pith-number/SADCSZHTIQMBRNOQ34CZ4O4SKA/graph.json","fetch_events":"https://pith.science/api/pith-number/SADCSZHTIQMBRNOQ34CZ4O4SKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA/action/storage_attestation","attest_author":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA/action/author_attestation","sign_citation":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA/action/citation_signature","submit_replication":"https://pith.science/pith/SADCSZHTIQMBRNOQ34CZ4O4SKA/action/replication_record"}},"created_at":"2026-07-05T08:22:13.361563+00:00","updated_at":"2026-07-05T08:22:13.361563+00:00"}