{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2OL3JY27XBVEMKEUS7IWOQFKD6","short_pith_number":"pith:2OL3JY27","schema_version":"1.0","canonical_sha256":"d397b4e35fb86a46289497d16740aa1f94b25060722354026a07d9a7a44c654b","source":{"kind":"arxiv","id":"2508.18507","version":1},"attestation_state":"computed","paper":{"title":"Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dillon Z. Chen, Johannes Zenn, Sheila A. McIlraith, Tristan Cinquin","submitted_at":"2025-08-25T21:28:14Z","abstract_excerpt":"We study the usage of language models (LMs) for planning over world models specified in the Planning Domain Definition Language (PDDL). We prompt LMs to generate Python programs that serve as generalised policies for solving PDDL problems from a given domain. Notably, our approach synthesises policies that are provably sound relative to the PDDL domain without reliance on external verifiers. We conduct experiments on competition benchmarks which show that our policies can solve more PDDL problems than PDDL planners and recent LM approaches within a fixed time and memory constraint. Our approac"},"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":"2508.18507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-25T21:28:14Z","cross_cats_sorted":[],"title_canon_sha256":"4743b735e25bd217d290e3c0fb2420b0966ed20c741787d2dcb8e58b656344d1","abstract_canon_sha256":"dc01c8ae5ce75c1abdddfb06391f6f040259f7a444ac43f4c837ea510ebb540b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:25.647470Z","signature_b64":"A3wz02ZbKeXeSM2kCpljJdfE1uCG8tQ1x6Am0oDyMn/oEplGs2rDO0CdDsDGNmnHh2VvHYArvMxdTbGjY9zLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d397b4e35fb86a46289497d16740aa1f94b25060722354026a07d9a7a44c654b","last_reissued_at":"2026-07-05T11:59:25.646985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:25.646985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dillon Z. Chen, Johannes Zenn, Sheila A. McIlraith, Tristan Cinquin","submitted_at":"2025-08-25T21:28:14Z","abstract_excerpt":"We study the usage of language models (LMs) for planning over world models specified in the Planning Domain Definition Language (PDDL). We prompt LMs to generate Python programs that serve as generalised policies for solving PDDL problems from a given domain. Notably, our approach synthesises policies that are provably sound relative to the PDDL domain without reliance on external verifiers. We conduct experiments on competition benchmarks which show that our policies can solve more PDDL problems than PDDL planners and recent LM approaches within a fixed time and memory constraint. Our approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18507","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/2508.18507/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":"2508.18507","created_at":"2026-07-05T11:59:25.647045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18507v1","created_at":"2026-07-05T11:59:25.647045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18507","created_at":"2026-07-05T11:59:25.647045+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OL3JY27XBVE","created_at":"2026-07-05T11:59:25.647045+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OL3JY27XBVEMKEU","created_at":"2026-07-05T11:59:25.647045+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OL3JY27","created_at":"2026-07-05T11:59:25.647045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16142","citing_title":"Property-Guided LLM Program Synthesis for Planning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6","json":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6.json","graph_json":"https://pith.science/api/pith-number/2OL3JY27XBVEMKEUS7IWOQFKD6/graph.json","events_json":"https://pith.science/api/pith-number/2OL3JY27XBVEMKEUS7IWOQFKD6/events.json","paper":"https://pith.science/paper/2OL3JY27"},"agent_actions":{"view_html":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6","download_json":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6.json","view_paper":"https://pith.science/paper/2OL3JY27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18507&json=true","fetch_graph":"https://pith.science/api/pith-number/2OL3JY27XBVEMKEUS7IWOQFKD6/graph.json","fetch_events":"https://pith.science/api/pith-number/2OL3JY27XBVEMKEUS7IWOQFKD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6/action/storage_attestation","attest_author":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6/action/author_attestation","sign_citation":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6/action/citation_signature","submit_replication":"https://pith.science/pith/2OL3JY27XBVEMKEUS7IWOQFKD6/action/replication_record"}},"created_at":"2026-07-05T11:59:25.647045+00:00","updated_at":"2026-07-05T11:59:25.647045+00:00"}