{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:23K2F2OPEI23FZ5J6UGGO26S3K","short_pith_number":"pith:23K2F2OP","schema_version":"1.0","canonical_sha256":"d6d5a2e9cf2235b2e7a9f50c676bd2da9addd6a736a992a9cfb4e93404908956","source":{"kind":"arxiv","id":"2404.11891","version":3},"attestation_state":"computed","paper":{"title":"Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Chuchu Fan, Yang Zhang, Yilun Hao, Yongchao Chen","submitted_at":"2024-04-18T04:36:37Z","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"},"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":"2404.11891","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T04:36:37Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"8d352f8b03edb9e4288861b35230c0b46fcee7a320d46f578f5a7d25dcf8d937","abstract_canon_sha256":"10a309effdf9f20b107f700d223542293dd3dbd8c1a880d5ed0d82cbc0a7a3bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:40.149288Z","signature_b64":"f189jz1A42QSYJh6HsLuU+j4Iec47nuMWP1wFyNK7kMWTULO+ngDKFPKKlbTOvf3CUYN4nv55MbxW66CVsQtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6d5a2e9cf2235b2e7a9f50c676bd2da9addd6a736a992a9cfb4e93404908956","last_reissued_at":"2026-07-05T10:06:40.148869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:40.148869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Chuchu Fan, Yang Zhang, Yilun Hao, Yongchao Chen","submitted_at":"2024-04-18T04:36:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11891","kind":"arxiv","version":3},"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/2404.11891/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":"2404.11891","created_at":"2026-07-05T10:06:40.148925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11891v3","created_at":"2026-07-05T10:06:40.148925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11891","created_at":"2026-07-05T10:06:40.148925+00:00"},{"alias_kind":"pith_short_12","alias_value":"23K2F2OPEI23","created_at":"2026-07-05T10:06:40.148925+00:00"},{"alias_kind":"pith_short_16","alias_value":"23K2F2OPEI23FZ5J","created_at":"2026-07-05T10:06:40.148925+00:00"},{"alias_kind":"pith_short_8","alias_value":"23K2F2OP","created_at":"2026-07-05T10:06:40.148925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05775","citing_title":"Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05080","citing_title":"Nidus: Externalized Reasoning for AI-Assisted Engineering","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K","json":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K.json","graph_json":"https://pith.science/api/pith-number/23K2F2OPEI23FZ5J6UGGO26S3K/graph.json","events_json":"https://pith.science/api/pith-number/23K2F2OPEI23FZ5J6UGGO26S3K/events.json","paper":"https://pith.science/paper/23K2F2OP"},"agent_actions":{"view_html":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K","download_json":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K.json","view_paper":"https://pith.science/paper/23K2F2OP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11891&json=true","fetch_graph":"https://pith.science/api/pith-number/23K2F2OPEI23FZ5J6UGGO26S3K/graph.json","fetch_events":"https://pith.science/api/pith-number/23K2F2OPEI23FZ5J6UGGO26S3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K/action/storage_attestation","attest_author":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K/action/author_attestation","sign_citation":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K/action/citation_signature","submit_replication":"https://pith.science/pith/23K2F2OPEI23FZ5J6UGGO26S3K/action/replication_record"}},"created_at":"2026-07-05T10:06:40.148925+00:00","updated_at":"2026-07-05T10:06:40.148925+00:00"}