{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:23K2F2OPEI23FZ5J6UGGO26S3K","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":"10a309effdf9f20b107f700d223542293dd3dbd8c1a880d5ed0d82cbc0a7a3bf","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T04:36:37Z","title_canon_sha256":"8d352f8b03edb9e4288861b35230c0b46fcee7a320d46f578f5a7d25dcf8d937"},"schema_version":"1.0","source":{"id":"2404.11891","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11891","created_at":"2026-07-05T10:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11891v3","created_at":"2026-07-05T10:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11891","created_at":"2026-07-05T10:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"23K2F2OPEI23","created_at":"2026-07-05T10:06:40Z"},{"alias_kind":"pith_short_16","alias_value":"23K2F2OPEI23FZ5J","created_at":"2026-07-05T10:06:40Z"},{"alias_kind":"pith_short_8","alias_value":"23K2F2OP","created_at":"2026-07-05T10:06:40Z"}],"graph_snapshots":[{"event_id":"sha256:b250e5c79e108be7ae159f1e5229fb424ebfb02792b40791f31a6fca0c18821f","target":"graph","created_at":"2026-07-05T10:06:40Z","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/2404.11891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) struggle to directly generate correct plans for complex multi-constraint planning problems, even with self-verification and self-critique. For example, a U.S. domestic travel planning benchmark TravelPlanner was proposed in Xie et al. (2024), where the best LLM OpenAI o1-preview can only find viable travel plans with a 10% success rate given all needed information. In this work, we tackle this by proposing an LLM-based planning framework that formalizes and solves complex multi-constraint planning problems as constrained satisfiability problems, which are further c","authors_text":"Chuchu Fan, Yang Zhang, Yilun Hao, Yongchao Chen","cross_cats":["cs.CL","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T04:36:37Z","title":"Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11891","kind":"arxiv","version":3},"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":"sha256:0fd01915b3af96eaed42ab613785c3f6f755f36ca7016b410cb976f7d4d29362","target":"record","created_at":"2026-07-05T10:06:40Z","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":"10a309effdf9f20b107f700d223542293dd3dbd8c1a880d5ed0d82cbc0a7a3bf","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T04:36:37Z","title_canon_sha256":"8d352f8b03edb9e4288861b35230c0b46fcee7a320d46f578f5a7d25dcf8d937"},"schema_version":"1.0","source":{"id":"2404.11891","kind":"arxiv","version":3}},"canonical_sha256":"d6d5a2e9cf2235b2e7a9f50c676bd2da9addd6a736a992a9cfb4e93404908956","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6d5a2e9cf2235b2e7a9f50c676bd2da9addd6a736a992a9cfb4e93404908956","first_computed_at":"2026-07-05T10:06:40.148869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:40.148869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f189jz1A42QSYJh6HsLuU+j4Iec47nuMWP1wFyNK7kMWTULO+ngDKFPKKlbTOvf3CUYN4nv55MbxW66CVsQtAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:40.149288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11891","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fd01915b3af96eaed42ab613785c3f6f755f36ca7016b410cb976f7d4d29362","sha256:b250e5c79e108be7ae159f1e5229fb424ebfb02792b40791f31a6fca0c18821f"],"state_sha256":"0fa818c80dd2892078bf4106f181d4d1600ae7287d6ea13d8036e5a42276b9ff"}