{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BDHQTE4J5BVVTWF2CYDETFNUGU","short_pith_number":"pith:BDHQTE4J","schema_version":"1.0","canonical_sha256":"08cf099389e86b59d8ba16064995b435100002e4684160e71378b4f19cefb65e","source":{"kind":"arxiv","id":"2506.11487","version":1},"attestation_state":"computed","paper":{"title":"Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenrui Cao, Fan Yang, Hui Xue, Liangcheng Song, Xian Zhang, Xinyi Le, Zenan Li","submitted_at":"2025-06-13T06:25:59Z","abstract_excerpt":"Recent advancements, such as DeepSeek-Prover-V2-671B and Kimina-Prover-Preview-72B, demonstrate a prevailing trend in leveraging reinforcement learning (RL)-based large-scale training for automated theorem proving. Surprisingly, we discover that even without any training, careful neuro-symbolic coordination of existing off-the-shelf reasoning models and tactic step provers can achieve comparable performance. This paper introduces \\textbf{DSP+}, an improved version of the Draft, Sketch, and Prove framework, featuring a \\emph{fine-grained and integrated} neuro-symbolic enhancement for each phase"},"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":"2506.11487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-13T06:25:59Z","cross_cats_sorted":[],"title_canon_sha256":"1e4e5da11b38dedccb7c2b4e4b057300977f1b4a7a7a5c1e02b34bae08b1201e","abstract_canon_sha256":"0706c9e440f0f5ada74f9a3a99aac232b5cb827cbc394311e9cc3fab21fbee9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:05.426228Z","signature_b64":"soHinKueYm17V/D6gFScEigbMXDl8rGCDdU3UtAV4j0iNPXtN76mH2O4jpIjd7vka5nye8DKK1Upd+8vTzrYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08cf099389e86b59d8ba16064995b435100002e4684160e71378b4f19cefb65e","last_reissued_at":"2026-07-05T11:21:05.425685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:05.425685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenrui Cao, Fan Yang, Hui Xue, Liangcheng Song, Xian Zhang, Xinyi Le, Zenan Li","submitted_at":"2025-06-13T06:25:59Z","abstract_excerpt":"Recent advancements, such as DeepSeek-Prover-V2-671B and Kimina-Prover-Preview-72B, demonstrate a prevailing trend in leveraging reinforcement learning (RL)-based large-scale training for automated theorem proving. Surprisingly, we discover that even without any training, careful neuro-symbolic coordination of existing off-the-shelf reasoning models and tactic step provers can achieve comparable performance. This paper introduces \\textbf{DSP+}, an improved version of the Draft, Sketch, and Prove framework, featuring a \\emph{fine-grained and integrated} neuro-symbolic enhancement for each phase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11487","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/2506.11487/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":"2506.11487","created_at":"2026-07-05T11:21:05.425754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11487v1","created_at":"2026-07-05T11:21:05.425754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11487","created_at":"2026-07-05T11:21:05.425754+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDHQTE4J5BVV","created_at":"2026-07-05T11:21:05.425754+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDHQTE4J5BVVTWF2","created_at":"2026-07-05T11:21:05.425754+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDHQTE4J","created_at":"2026-07-05T11:21:05.425754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07779","citing_title":"From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2602.24273","citing_title":"A Minimal Agent for Automated Theorem Proving","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19715","citing_title":"Neuro-Symbolic Proof Generation for Scaling Systems Software Verification","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU","json":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU.json","graph_json":"https://pith.science/api/pith-number/BDHQTE4J5BVVTWF2CYDETFNUGU/graph.json","events_json":"https://pith.science/api/pith-number/BDHQTE4J5BVVTWF2CYDETFNUGU/events.json","paper":"https://pith.science/paper/BDHQTE4J"},"agent_actions":{"view_html":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU","download_json":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU.json","view_paper":"https://pith.science/paper/BDHQTE4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11487&json=true","fetch_graph":"https://pith.science/api/pith-number/BDHQTE4J5BVVTWF2CYDETFNUGU/graph.json","fetch_events":"https://pith.science/api/pith-number/BDHQTE4J5BVVTWF2CYDETFNUGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU/action/storage_attestation","attest_author":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU/action/author_attestation","sign_citation":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU/action/citation_signature","submit_replication":"https://pith.science/pith/BDHQTE4J5BVVTWF2CYDETFNUGU/action/replication_record"}},"created_at":"2026-07-05T11:21:05.425754+00:00","updated_at":"2026-07-05T11:21:05.425754+00:00"}