{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DTINKQS5IM2L4MFEVRCWMM2Z3H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"acf18ca6d3c4aefe1e56451907ee9e9adf9aa89b803975eec9e55ab3d656d5a8","cross_cats_sorted":["cs.CL","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T15:18:45Z","title_canon_sha256":"635831c300b28016780559cfd917ac4e49ce998627aad05ae67a6ac4e7860867"},"schema_version":"1.0","source":{"id":"2605.28602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28602","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28602v1","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28602","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"DTINKQS5IM2L","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"DTINKQS5IM2L4MFE","created_at":"2026-05-28T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"DTINKQS5","created_at":"2026-05-28T02:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:4cbe599fcc711512802a03668476f34651b6e1e333893b0b95295a483b3e3673","target":"graph","created_at":"2026-05-28T02:04:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.28602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Leizhen Zhang, Sheng Chen, Shuhan Chen","cross_cats":["cs.CL","cs.LO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T15:18:45Z","title":"Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28602","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:83c7f58bfc68ac559be6ba8a7d156390542af09d9b98684d230fd2c8e106244e","target":"record","created_at":"2026-05-28T02:04:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"acf18ca6d3c4aefe1e56451907ee9e9adf9aa89b803975eec9e55ab3d656d5a8","cross_cats_sorted":["cs.CL","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T15:18:45Z","title_canon_sha256":"635831c300b28016780559cfd917ac4e49ce998627aad05ae67a6ac4e7860867"},"schema_version":"1.0","source":{"id":"2605.28602","kind":"arxiv","version":1}},"canonical_sha256":"1cd0d5425d4334be30a4ac45663359d9de6a574401d032c64049dda8c3bcaec2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cd0d5425d4334be30a4ac45663359d9de6a574401d032c64049dda8c3bcaec2","first_computed_at":"2026-05-28T02:04:57.511289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:57.511289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zEyLMOSpAEArZOs3zfLnU/B1w4KlDXjt+Bh86sWPclHuQSDj1INheb5XLHjfbbAHcsWah6U0TN6C2X0GMF5KCw==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:57.511732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83c7f58bfc68ac559be6ba8a7d156390542af09d9b98684d230fd2c8e106244e","sha256:4cbe599fcc711512802a03668476f34651b6e1e333893b0b95295a483b3e3673"],"state_sha256":"197cf2f3288e1f21bf5eeb8a497af32a575df21d8f3095c233ad0084d8c4e8cb"}