{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QN4SSKLKH3ZABYPDWNYXZYU54W","short_pith_number":"pith:QN4SSKLK","schema_version":"1.0","canonical_sha256":"837929296a3ef200e1e3b3717ce29de594c10ea7feab2058f5f7fd046526fcd7","source":{"kind":"arxiv","id":"2309.05689","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model for Science: A Study on P vs. NP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Guangyan Zhou, Ke Xu, Li Dong, Qingxiu Dong, Yaru Hao, Zhifang Sui","submitted_at":"2023-09-11T17:49:27Z","abstract_excerpt":"In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics. Specifically, we propose Socratic reasoning, a general framework that promotes in-depth thinking with LLMs for complex problem-solving. Socratic reasoning encourages LLMs to recursively discover, solve, and integrate problems while facilitating self-evaluation and refinement. Our pilot study on the P vs. NP problem shows that GPT-4 successfully produces a proof schema and engages in rigorous rea"},"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":"2309.05689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T17:49:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"543fdb1d2b3c508314398366028931877ad8ac7e17ac216551f1a3b9755a9daa","abstract_canon_sha256":"0c97b421436d9bca80851151ec7de01ad7cc526a31ddf3835c484bcb411e7d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:45.160066Z","signature_b64":"PrF9a5MpB5o3KDGHWx4e5lQ7AAJsxbpIx/uZ1yt3MKQkBrU12OQcfvUIrWZJqtiEJzpeo3EUcIdJExsIBZDcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"837929296a3ef200e1e3b3717ce29de594c10ea7feab2058f5f7fd046526fcd7","last_reissued_at":"2026-07-05T06:49:45.159667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:45.159667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model for Science: A Study on P vs. NP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Guangyan Zhou, Ke Xu, Li Dong, Qingxiu Dong, Yaru Hao, Zhifang Sui","submitted_at":"2023-09-11T17:49:27Z","abstract_excerpt":"In this work, we use large language models (LLMs) to augment and accelerate research on the P versus NP problem, one of the most important open problems in theoretical computer science and mathematics. Specifically, we propose Socratic reasoning, a general framework that promotes in-depth thinking with LLMs for complex problem-solving. Socratic reasoning encourages LLMs to recursively discover, solve, and integrate problems while facilitating self-evaluation and refinement. Our pilot study on the P vs. NP problem shows that GPT-4 successfully produces a proof schema and engages in rigorous rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05689","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/2309.05689/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":"2309.05689","created_at":"2026-07-05T06:49:45.159719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.05689v1","created_at":"2026-07-05T06:49:45.159719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05689","created_at":"2026-07-05T06:49:45.159719+00:00"},{"alias_kind":"pith_short_12","alias_value":"QN4SSKLKH3ZA","created_at":"2026-07-05T06:49:45.159719+00:00"},{"alias_kind":"pith_short_16","alias_value":"QN4SSKLKH3ZABYPD","created_at":"2026-07-05T06:49:45.159719+00:00"},{"alias_kind":"pith_short_8","alias_value":"QN4SSKLK","created_at":"2026-07-05T06:49:45.159719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.14702","citing_title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02255","citing_title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W","json":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W.json","graph_json":"https://pith.science/api/pith-number/QN4SSKLKH3ZABYPDWNYXZYU54W/graph.json","events_json":"https://pith.science/api/pith-number/QN4SSKLKH3ZABYPDWNYXZYU54W/events.json","paper":"https://pith.science/paper/QN4SSKLK"},"agent_actions":{"view_html":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W","download_json":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W.json","view_paper":"https://pith.science/paper/QN4SSKLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.05689&json=true","fetch_graph":"https://pith.science/api/pith-number/QN4SSKLKH3ZABYPDWNYXZYU54W/graph.json","fetch_events":"https://pith.science/api/pith-number/QN4SSKLKH3ZABYPDWNYXZYU54W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W/action/storage_attestation","attest_author":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W/action/author_attestation","sign_citation":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W/action/citation_signature","submit_replication":"https://pith.science/pith/QN4SSKLKH3ZABYPDWNYXZYU54W/action/replication_record"}},"created_at":"2026-07-05T06:49:45.159719+00:00","updated_at":"2026-07-05T06:49:45.159719+00:00"}