{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GG2BKORGPBXO76QYEC52X37TCC","short_pith_number":"pith:GG2BKORG","schema_version":"1.0","canonical_sha256":"31b4153a26786eeffa1820bbabeff3108912ce88887f2940c6a4eda89386bdbe","source":{"kind":"arxiv","id":"2505.20869","version":1},"attestation_state":"computed","paper":{"title":"Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kuo Zhou, Lu Zhang","submitted_at":"2025-05-27T08:21:07Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated formidable capabilities in solving mathematical problems, yet they may still commit logical reasoning and computational errors during the problem-solving process. Thus, this paper proposes a framework, MATH-VF, which includes a Formalizer and a Critic, for formally verifying the correctness of the solutions generated by large language models. Our framework first utilizes a Formalizer which employs an LLM to translate a natural language solution into a formal context. Afterward, our Critic (which integrates various external tools such as a Computer"},"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":"2505.20869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T08:21:07Z","cross_cats_sorted":[],"title_canon_sha256":"23976bf43442dbab9d1032107f3b1f2f16a707299020d6f4d2685246632e91c8","abstract_canon_sha256":"d6491a9a62396017d0882f1b642c74481e6815f0ef78ffcbe82530f43b8153c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:20.139424Z","signature_b64":"A3niun0vgMJpA1wdn8Bb2NjxAChuGx63ftXie/mMr94T3Gaon6eR59aroNiZxWp1b3xmUMlkqJdvtrSDn6tnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31b4153a26786eeffa1820bbabeff3108912ce88887f2940c6a4eda89386bdbe","last_reissued_at":"2026-07-05T11:10:20.138915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:20.138915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kuo Zhou, Lu Zhang","submitted_at":"2025-05-27T08:21:07Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated formidable capabilities in solving mathematical problems, yet they may still commit logical reasoning and computational errors during the problem-solving process. Thus, this paper proposes a framework, MATH-VF, which includes a Formalizer and a Critic, for formally verifying the correctness of the solutions generated by large language models. Our framework first utilizes a Formalizer which employs an LLM to translate a natural language solution into a formal context. Afterward, our Critic (which integrates various external tools such as a Computer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20869","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/2505.20869/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":"2505.20869","created_at":"2026-07-05T11:10:20.138974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20869v1","created_at":"2026-07-05T11:10:20.138974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20869","created_at":"2026-07-05T11:10:20.138974+00:00"},{"alias_kind":"pith_short_12","alias_value":"GG2BKORGPBXO","created_at":"2026-07-05T11:10:20.138974+00:00"},{"alias_kind":"pith_short_16","alias_value":"GG2BKORGPBXO76QY","created_at":"2026-07-05T11:10:20.138974+00:00"},{"alias_kind":"pith_short_8","alias_value":"GG2BKORG","created_at":"2026-07-05T11:10:20.138974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01223","citing_title":"Theoria: Rewrite-Acceptability Verification over Informal Reasoning States","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22875","citing_title":"RMA: an Agentic System for Research-Level Mathematical Problems","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC","json":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC.json","graph_json":"https://pith.science/api/pith-number/GG2BKORGPBXO76QYEC52X37TCC/graph.json","events_json":"https://pith.science/api/pith-number/GG2BKORGPBXO76QYEC52X37TCC/events.json","paper":"https://pith.science/paper/GG2BKORG"},"agent_actions":{"view_html":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC","download_json":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC.json","view_paper":"https://pith.science/paper/GG2BKORG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20869&json=true","fetch_graph":"https://pith.science/api/pith-number/GG2BKORGPBXO76QYEC52X37TCC/graph.json","fetch_events":"https://pith.science/api/pith-number/GG2BKORGPBXO76QYEC52X37TCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC/action/storage_attestation","attest_author":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC/action/author_attestation","sign_citation":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC/action/citation_signature","submit_replication":"https://pith.science/pith/GG2BKORGPBXO76QYEC52X37TCC/action/replication_record"}},"created_at":"2026-07-05T11:10:20.138974+00:00","updated_at":"2026-07-05T11:10:20.138974+00:00"}