{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DTINKQS5IM2L4MFEVRCWMM2Z3H","short_pith_number":"pith:DTINKQS5","schema_version":"1.0","canonical_sha256":"1cd0d5425d4334be30a4ac45663359d9de6a574401d032c64049dda8c3bcaec2","source":{"kind":"arxiv","id":"2605.28602","version":1},"attestation_state":"computed","paper":{"title":"Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LO"],"primary_cat":"cs.AI","authors_text":"Leizhen Zhang, Sheng Chen, Shuhan Chen","submitted_at":"2026-05-27T15:18:45Z","abstract_excerpt":"Large language models (LLMs) are increasingly used for tasks that implicitly reduce to Boolean satisfiability (SAT), yet their reasoning ability on SAT remains unclear. We present a systematic study of LLMs on 2-SAT and 3-SAT, together with two canonical reductions, Vertex Cover and discrete 3D packing, to probe representation-invariant reasoning. We first evaluate models using conventional metrics, including accuracy, precision, recall, and F1, as well as the SAT phase-transition setting. We find that these metrics can be misleading: many models obtain high scores by over-predicting satisfiab"},"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":"2605.28602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T15:18:45Z","cross_cats_sorted":["cs.CL","cs.LO"],"title_canon_sha256":"635831c300b28016780559cfd917ac4e49ce998627aad05ae67a6ac4e7860867","abstract_canon_sha256":"acf18ca6d3c4aefe1e56451907ee9e9adf9aa89b803975eec9e55ab3d656d5a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:57.511732Z","signature_b64":"zEyLMOSpAEArZOs3zfLnU/B1w4KlDXjt+Bh86sWPclHuQSDj1INheb5XLHjfbbAHcsWah6U0TN6C2X0GMF5KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cd0d5425d4334be30a4ac45663359d9de6a574401d032c64049dda8c3bcaec2","last_reissued_at":"2026-05-28T02:04:57.511289Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:57.511289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LO"],"primary_cat":"cs.AI","authors_text":"Leizhen Zhang, Sheng Chen, Shuhan Chen","submitted_at":"2026-05-27T15:18:45Z","abstract_excerpt":"Large language models (LLMs) are increasingly used for tasks that implicitly reduce to Boolean satisfiability (SAT), yet their reasoning ability on SAT remains unclear. We present a systematic study of LLMs on 2-SAT and 3-SAT, together with two canonical reductions, Vertex Cover and discrete 3D packing, to probe representation-invariant reasoning. We first evaluate models using conventional metrics, including accuracy, precision, recall, and F1, as well as the SAT phase-transition setting. We find that these metrics can be misleading: many models obtain high scores by over-predicting satisfiab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28602","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/2605.28602/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":"2605.28602","created_at":"2026-05-28T02:04:57.511368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28602v1","created_at":"2026-05-28T02:04:57.511368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28602","created_at":"2026-05-28T02:04:57.511368+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTINKQS5IM2L","created_at":"2026-05-28T02:04:57.511368+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTINKQS5IM2L4MFE","created_at":"2026-05-28T02:04:57.511368+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTINKQS5","created_at":"2026-05-28T02:04:57.511368+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/DTINKQS5IM2L4MFEVRCWMM2Z3H","json":"https://pith.science/pith/DTINKQS5IM2L4MFEVRCWMM2Z3H.json","graph_json":"https://pith.science/api/pith-number/DTINKQS5IM2L4MFEVRCWMM2Z3H/graph.json","events_json":"https://pith.science/api/pith-number/DTINKQS5IM2L4MFEVRCWMM2Z3H/events.json","paper":"https://pith.science/paper/DTINKQS5"},"agent_actions":{"view_html":"https://pith.science/pith/DTINKQS5IM2L4MFEVRCWMM2Z3H","download_json":"https://pith.science/pith/DTINKQS5IM2L4MFEVRCWMM2Z3H.json","view_paper":"https://pith.science/paper/DTINKQS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28602&json=true","fetch_graph":"https://pith.science/api/pith-number/DTINKQS5IM2L4MFEVRCWMM2Z3H/graph.json","fetch_events":"https://pith.science/api/pith-number/DTINKQS5IM2L4MFEVRCWMM2Z3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTINKQS5IM2L4MFEVRCWMM2Z3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTINKQS5IM2L4MFEVRCWMM2Z3H/action/storage_attestation","attest_author":"https://pith.science/pith/DTINKQS5IM2L4MFEVRCWMM2Z3H/action/author_attestation","sign_citation":"https://pith.science/pith/DTINKQS5IM2L4MFEVRCWMM2Z3H/action/citation_signature","submit_replication":"https://pith.science/pith/DTINKQS5IM2L4MFEVRCWMM2Z3H/action/replication_record"}},"created_at":"2026-05-28T02:04:57.511368+00:00","updated_at":"2026-05-28T02:04:57.511368+00:00"}