{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T2DCHUZCVAZRS5IKYEINATWWV2","short_pith_number":"pith:T2DCHUZC","schema_version":"1.0","canonical_sha256":"9e8623d322a83319750ac110d04ed6ae93bf3f5ec53b1daffaf1a6078735746f","source":{"kind":"arxiv","id":"2502.20175","version":1},"attestation_state":"computed","paper":{"title":"An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Damien Graux, Jeff Z. Pan, Kaustubh Vyas, Keshuang Li, Pavlos Vougiouklis, Ruofei Lai, S\\'ebastien Montella, Yang Ren","submitted_at":"2025-02-27T15:13:07Z","abstract_excerpt":"In recent advancements, large language models (LLMs) have exhibited proficiency in code generation and chain-of-thought reasoning, laying the groundwork for tackling automatic formal planning tasks. This study evaluates the potential of LLMs to understand and generate Planning Domain Definition Language (PDDL), an essential representation in artificial intelligence planning. We conduct an extensive analysis across 20 distinct models spanning 7 major LLM families, both commercial and open-source. Our comprehensive evaluation sheds light on the zero-shot LLM capabilities of parsing, generating, "},"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":"2502.20175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T15:13:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4c1cdcb7afeff3cc63697f47bf31fd36323275144484adcc1e3e1c5b9265c224","abstract_canon_sha256":"7a8fe5b012e9434ba50fb39e5189cbf2da7a92cafaf8f6db84aa9eac832b8825"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:10.471553Z","signature_b64":"WpTU3+AQVbRI7ll9Zht3Dl2n8WPnvQedAzMWhL6FkLQH7hQ3XY784f6OQBC0zPimV8q7cqF+782SdE+EMunwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e8623d322a83319750ac110d04ed6ae93bf3f5ec53b1daffaf1a6078735746f","last_reissued_at":"2026-07-05T10:21:10.471028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:10.471028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Damien Graux, Jeff Z. Pan, Kaustubh Vyas, Keshuang Li, Pavlos Vougiouklis, Ruofei Lai, S\\'ebastien Montella, Yang Ren","submitted_at":"2025-02-27T15:13:07Z","abstract_excerpt":"In recent advancements, large language models (LLMs) have exhibited proficiency in code generation and chain-of-thought reasoning, laying the groundwork for tackling automatic formal planning tasks. This study evaluates the potential of LLMs to understand and generate Planning Domain Definition Language (PDDL), an essential representation in artificial intelligence planning. We conduct an extensive analysis across 20 distinct models spanning 7 major LLM families, both commercial and open-source. Our comprehensive evaluation sheds light on the zero-shot LLM capabilities of parsing, generating, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20175","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/2502.20175/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":"2502.20175","created_at":"2026-07-05T10:21:10.471100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20175v1","created_at":"2026-07-05T10:21:10.471100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20175","created_at":"2026-07-05T10:21:10.471100+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2DCHUZCVAZR","created_at":"2026-07-05T10:21:10.471100+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2DCHUZCVAZRS5IK","created_at":"2026-07-05T10:21:10.471100+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2DCHUZC","created_at":"2026-07-05T10:21:10.471100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21092","citing_title":"Mind the Prompt: Self-adaptive Generation of Task Plan Explanations via LLMs","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17957","citing_title":"Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2","json":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2.json","graph_json":"https://pith.science/api/pith-number/T2DCHUZCVAZRS5IKYEINATWWV2/graph.json","events_json":"https://pith.science/api/pith-number/T2DCHUZCVAZRS5IKYEINATWWV2/events.json","paper":"https://pith.science/paper/T2DCHUZC"},"agent_actions":{"view_html":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2","download_json":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2.json","view_paper":"https://pith.science/paper/T2DCHUZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20175&json=true","fetch_graph":"https://pith.science/api/pith-number/T2DCHUZCVAZRS5IKYEINATWWV2/graph.json","fetch_events":"https://pith.science/api/pith-number/T2DCHUZCVAZRS5IKYEINATWWV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2/action/storage_attestation","attest_author":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2/action/author_attestation","sign_citation":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2/action/citation_signature","submit_replication":"https://pith.science/pith/T2DCHUZCVAZRS5IKYEINATWWV2/action/replication_record"}},"created_at":"2026-07-05T10:21:10.471100+00:00","updated_at":"2026-07-05T10:21:10.471100+00:00"}