{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GPIXCAQUAZO5QM2CWRCO323ZGA","short_pith_number":"pith:GPIXCAQU","schema_version":"1.0","canonical_sha256":"33d1710214065dd83342b444edeb793028b88bc21e83de3d7ec9eebf0c5b10a0","source":{"kind":"arxiv","id":"2412.10675","version":1},"attestation_state":"computed","paper":{"title":"Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Nir Lipovetzky, Sukai Huang, Trevor Cohn","submitted_at":"2024-12-14T04:23:14Z","abstract_excerpt":"The capability of Large Language Models (LLMs) to plan remains a topic of debate. Some critics argue that strategies to boost LLMs' reasoning skills are ineffective in planning tasks, while others report strong outcomes merely from training models on a planning corpus. This study reassesses recent strategies by developing an end-to-end LLM planner and employing diverse metrics for a thorough evaluation. We find that merely fine-tuning LLMs on a corpus of planning instances does not lead to robust planning skills, as indicated by poor performance on out-of-distribution test sets. At the same ti"},"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":"2412.10675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T04:23:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b7554b20487fc506cf1c0229dd26965e4ea7703ac6e2e48f175801901089b29","abstract_canon_sha256":"ce1e450d3e4ddd89e1a63bbb826b0c2d257a226f9f735d2bc34469f9d835416a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:19.517813Z","signature_b64":"0g5Qh2mtq54/QNcsIHuQoITHFZXI5ADAWz+5wPSVKfwsOHI/cAFAnNP9B4hV/4UtG24g/0YF/Dj0eFa3EVaQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33d1710214065dd83342b444edeb793028b88bc21e83de3d7ec9eebf0c5b10a0","last_reissued_at":"2026-07-05T09:49:19.517223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:19.517223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Nir Lipovetzky, Sukai Huang, Trevor Cohn","submitted_at":"2024-12-14T04:23:14Z","abstract_excerpt":"The capability of Large Language Models (LLMs) to plan remains a topic of debate. Some critics argue that strategies to boost LLMs' reasoning skills are ineffective in planning tasks, while others report strong outcomes merely from training models on a planning corpus. This study reassesses recent strategies by developing an end-to-end LLM planner and employing diverse metrics for a thorough evaluation. We find that merely fine-tuning LLMs on a corpus of planning instances does not lead to robust planning skills, as indicated by poor performance on out-of-distribution test sets. At the same ti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10675","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/2412.10675/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":"2412.10675","created_at":"2026-07-05T09:49:19.517288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10675v1","created_at":"2026-07-05T09:49:19.517288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10675","created_at":"2026-07-05T09:49:19.517288+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPIXCAQUAZO5","created_at":"2026-07-05T09:49:19.517288+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPIXCAQUAZO5QM2C","created_at":"2026-07-05T09:49:19.517288+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPIXCAQU","created_at":"2026-07-05T09:49:19.517288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03685","citing_title":"A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16142","citing_title":"Property-Guided LLM Program Synthesis for Planning","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA","json":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA.json","graph_json":"https://pith.science/api/pith-number/GPIXCAQUAZO5QM2CWRCO323ZGA/graph.json","events_json":"https://pith.science/api/pith-number/GPIXCAQUAZO5QM2CWRCO323ZGA/events.json","paper":"https://pith.science/paper/GPIXCAQU"},"agent_actions":{"view_html":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA","download_json":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA.json","view_paper":"https://pith.science/paper/GPIXCAQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10675&json=true","fetch_graph":"https://pith.science/api/pith-number/GPIXCAQUAZO5QM2CWRCO323ZGA/graph.json","fetch_events":"https://pith.science/api/pith-number/GPIXCAQUAZO5QM2CWRCO323ZGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA/action/storage_attestation","attest_author":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA/action/author_attestation","sign_citation":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA/action/citation_signature","submit_replication":"https://pith.science/pith/GPIXCAQUAZO5QM2CWRCO323ZGA/action/replication_record"}},"created_at":"2026-07-05T09:49:19.517288+00:00","updated_at":"2026-07-05T09:49:19.517288+00:00"}