{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6XA4IT2SPWXGT6CAAS62QMMTM6","short_pith_number":"pith:6XA4IT2S","schema_version":"1.0","canonical_sha256":"f5c1c44f527dae69f84004bda8319367a5276845871865255d3afe10b87f56b6","source":{"kind":"arxiv","id":"2210.12283","version":3},"attestation_state":"computed","paper":{"title":"Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Albert Q. Jiang, Guillaume Lample, Jiacheng Liu, Jin Peng Zhou, Mateja Jamnik, Sean Welleck, Timoth\\'ee Lacroix, Wenda Li, Yuhuai Wu","submitted_at":"2022-10-21T22:37:22Z","abstract_excerpt":"The formalization of existing mathematical proofs is a notoriously difficult process. Despite decades of research on automation and proof assistants, writing formal proofs remains arduous and only accessible to a few experts. While previous studies to automate formalization focused on powerful search algorithms, no attempts were made to take advantage of available informal proofs. In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problem"},"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":"2210.12283","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-21T22:37:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"25c05387adf2d963792aadc78fbb189a556c988c16afb84b32fa10e415c10113","abstract_canon_sha256":"2376ca8ac7ad1a5e53da78b0a14fc9a650faa09c44bcbd9aa27379819f1e27ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:16.387929Z","signature_b64":"4e7kbWFxHkTfoY50YrYRk1wq6/6SrnsIdvOd9y/sIBC/tlXZwipIMtS1d7VL1pOXItP/W/eaFzc1dCmh9RErDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5c1c44f527dae69f84004bda8319367a5276845871865255d3afe10b87f56b6","last_reissued_at":"2026-07-05T05:43:16.387431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:16.387431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Albert Q. Jiang, Guillaume Lample, Jiacheng Liu, Jin Peng Zhou, Mateja Jamnik, Sean Welleck, Timoth\\'ee Lacroix, Wenda Li, Yuhuai Wu","submitted_at":"2022-10-21T22:37:22Z","abstract_excerpt":"The formalization of existing mathematical proofs is a notoriously difficult process. Despite decades of research on automation and proof assistants, writing formal proofs remains arduous and only accessible to a few experts. While previous studies to automate formalization focused on powerful search algorithms, no attempts were made to take advantage of available informal proofs. In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12283","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/2210.12283/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":"2210.12283","created_at":"2026-07-05T05:43:16.387497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12283v3","created_at":"2026-07-05T05:43:16.387497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12283","created_at":"2026-07-05T05:43:16.387497+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XA4IT2SPWXG","created_at":"2026-07-05T05:43:16.387497+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XA4IT2SPWXGT6CA","created_at":"2026-07-05T05:43:16.387497+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XA4IT2S","created_at":"2026-07-05T05:43:16.387497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06468","citing_title":"Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05400","citing_title":"LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03743","citing_title":"Proof-Refactor: Refactoring Generated Formal Proofs into Modular Artifacts","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22763","citing_title":"Advancing Mathematics Research with AI-Driven Formal Proof Search","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28841","citing_title":"LAMP: Lean-based Agentic framework with MCP and Proof Repair","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29687","citing_title":"A Machine-Verified Proof of a Quantum-Optimization Conjecture","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29251","citing_title":"Provably Secure Agent Guardrail","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30914","citing_title":"Automating Formal Verification with Reinforcement Learning and Recursive Inference","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22885","citing_title":"ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23109","citing_title":"Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2402.03300","citing_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22763","citing_title":"Advancing Mathematics Research with AI-Driven Formal Proof Search","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17246","citing_title":"Fidelity Probes for Specification--Code Alignment","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20055","citing_title":"VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.24273","citing_title":"A Minimal Agent for Automated Theorem Proving","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2305.18323","citing_title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01346","citing_title":"Aristotle: IMO-level Automated Theorem Proving","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14972","citing_title":"Viverra: Text-to-Code with Guarantees","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13817","citing_title":"Neurosymbolic Auditing of Natural-Language Software Requirements","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03071","citing_title":"Automatic Textbook Formalization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11905","citing_title":"Rethinking Supervision Granularity: Segment-Level Learning for LLM-Based Theorem Proving","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25155","citing_title":"Rethinking Wireless Communications through Formal Mathematical AI Reasoning","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19558","citing_title":"On Reasoning-Centric LLM-based Automated Theorem Proving","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6","json":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6.json","graph_json":"https://pith.science/api/pith-number/6XA4IT2SPWXGT6CAAS62QMMTM6/graph.json","events_json":"https://pith.science/api/pith-number/6XA4IT2SPWXGT6CAAS62QMMTM6/events.json","paper":"https://pith.science/paper/6XA4IT2S"},"agent_actions":{"view_html":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6","download_json":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6.json","view_paper":"https://pith.science/paper/6XA4IT2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12283&json=true","fetch_graph":"https://pith.science/api/pith-number/6XA4IT2SPWXGT6CAAS62QMMTM6/graph.json","fetch_events":"https://pith.science/api/pith-number/6XA4IT2SPWXGT6CAAS62QMMTM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6/action/storage_attestation","attest_author":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6/action/author_attestation","sign_citation":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6/action/citation_signature","submit_replication":"https://pith.science/pith/6XA4IT2SPWXGT6CAAS62QMMTM6/action/replication_record"}},"created_at":"2026-07-05T05:43:16.387497+00:00","updated_at":"2026-07-05T05:43:16.387497+00:00"}