{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7F4MJR56KG4AGD3DT6THVEHFB7","short_pith_number":"pith:7F4MJR56","schema_version":"1.0","canonical_sha256":"f978c4c7be51b8030f639fa67a90e50fe448aacdb6cc4833eb56db2ef45b633d","source":{"kind":"arxiv","id":"2507.02541","version":1},"attestation_state":"computed","paper":{"title":"Clarifying Before Reasoning: A Coq Prover with Structural Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrew Chi-Chih Yao, Biao Li, Chao Li, Chenxu Fu, Ge Zhang, Hanbin Yang, Xiaodie Wang, Yang Yuan, Yanzhen Lu","submitted_at":"2025-07-03T11:35:34Z","abstract_excerpt":"In this work, we investigate whether improving task clarity can enhance reasoning ability of large language models, focusing on theorem proving in Coq. We introduce a concept-level metric to evaluate task clarity and show that adding structured semantic context to the standard input used by modern LLMs, leads to a 1.85$\\times$ improvement in clarity score (44.5\\%~$\\rightarrow$~82.3\\%). Using the general-purpose model \\texttt{DeepSeek-V3}, our approach leads to a 2.1$\\times$ improvement in proof success (21.8\\%~$\\rightarrow$~45.8\\%) and outperforms the previous state-of-the-art \\texttt{Graph2Ta"},"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":"2507.02541","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-03T11:35:34Z","cross_cats_sorted":[],"title_canon_sha256":"eb7f5d7825d8a4a8d17c447913ac9120093430834148e8b4e3473af751df2593","abstract_canon_sha256":"0a0fa2df28f5f6b454ba142c276c11f0853a73d54e9e9ff3b7c38e4b5f62f2fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:30.432185Z","signature_b64":"cQk6BHr96b0yiOsp68Ppvpxi01tF8ngIaufVsEav1W3PiRHJRWlFYi/JbzRJSLD47QfV493r7XAzDraOypWlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f978c4c7be51b8030f639fa67a90e50fe448aacdb6cc4833eb56db2ef45b633d","last_reissued_at":"2026-07-05T11:31:30.431673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:30.431673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clarifying Before Reasoning: A Coq Prover with Structural Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrew Chi-Chih Yao, Biao Li, Chao Li, Chenxu Fu, Ge Zhang, Hanbin Yang, Xiaodie Wang, Yang Yuan, Yanzhen Lu","submitted_at":"2025-07-03T11:35:34Z","abstract_excerpt":"In this work, we investigate whether improving task clarity can enhance reasoning ability of large language models, focusing on theorem proving in Coq. We introduce a concept-level metric to evaluate task clarity and show that adding structured semantic context to the standard input used by modern LLMs, leads to a 1.85$\\times$ improvement in clarity score (44.5\\%~$\\rightarrow$~82.3\\%). Using the general-purpose model \\texttt{DeepSeek-V3}, our approach leads to a 2.1$\\times$ improvement in proof success (21.8\\%~$\\rightarrow$~45.8\\%) and outperforms the previous state-of-the-art \\texttt{Graph2Ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02541","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/2507.02541/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":"2507.02541","created_at":"2026-07-05T11:31:30.431758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02541v1","created_at":"2026-07-05T11:31:30.431758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02541","created_at":"2026-07-05T11:31:30.431758+00:00"},{"alias_kind":"pith_short_12","alias_value":"7F4MJR56KG4A","created_at":"2026-07-05T11:31:30.431758+00:00"},{"alias_kind":"pith_short_16","alias_value":"7F4MJR56KG4AGD3D","created_at":"2026-07-05T11:31:30.431758+00:00"},{"alias_kind":"pith_short_8","alias_value":"7F4MJR56","created_at":"2026-07-05T11:31:30.431758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7","json":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7.json","graph_json":"https://pith.science/api/pith-number/7F4MJR56KG4AGD3DT6THVEHFB7/graph.json","events_json":"https://pith.science/api/pith-number/7F4MJR56KG4AGD3DT6THVEHFB7/events.json","paper":"https://pith.science/paper/7F4MJR56"},"agent_actions":{"view_html":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7","download_json":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7.json","view_paper":"https://pith.science/paper/7F4MJR56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02541&json=true","fetch_graph":"https://pith.science/api/pith-number/7F4MJR56KG4AGD3DT6THVEHFB7/graph.json","fetch_events":"https://pith.science/api/pith-number/7F4MJR56KG4AGD3DT6THVEHFB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7/action/storage_attestation","attest_author":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7/action/author_attestation","sign_citation":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7/action/citation_signature","submit_replication":"https://pith.science/pith/7F4MJR56KG4AGD3DT6THVEHFB7/action/replication_record"}},"created_at":"2026-07-05T11:31:30.431758+00:00","updated_at":"2026-07-05T11:31:30.431758+00:00"}