{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KXBLHR3DXLCGZYK6LGHIN47P2X","short_pith_number":"pith:KXBLHR3D","schema_version":"1.0","canonical_sha256":"55c2b3c763bac46ce15e598e86f3efd5f5f1ade37dfc05757bbd9b8918282771","source":{"kind":"arxiv","id":"2310.08118","version":1},"attestation_state":"computed","paper":{"title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Karthik Valmeekam, Matthew Marquez, Subbarao Kambhampati","submitted_at":"2023-10-12T08:22:37Z","abstract_excerpt":"There have been widespread claims about Large Language Models (LLMs) being able to successfully verify or self-critique their candidate solutions in reasoning problems in an iterative mode. Intrigued by those claims, in this paper we set out to investigate the verification/self-critiquing abilities of large language models in the context of planning. We evaluate a planning system that employs LLMs for both plan generation and verification. We assess the verifier LLM's performance against ground-truth verification, the impact of self-critiquing on plan generation, and the influence of varying f"},"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":"2310.08118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T08:22:37Z","cross_cats_sorted":[],"title_canon_sha256":"7af771630f642e56a4ccdf38c174a6efb4f2946fab383775d137525fde68f4f7","abstract_canon_sha256":"7e2901d8293721d5c65c4cfbf6f268e4355e26570f2f0841ff5662ca54d7b4ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:10.328540Z","signature_b64":"Cb4R1hxJnNENlzpulIfT9T+5oScjVcF4TXKGau2dGg5S1RdTVimDCFWuY1MbfEg+gETe8GjWWZNv7gEcdCRZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55c2b3c763bac46ce15e598e86f3efd5f5f1ade37dfc05757bbd9b8918282771","last_reissued_at":"2026-07-05T07:00:10.328055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:10.328055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Karthik Valmeekam, Matthew Marquez, Subbarao Kambhampati","submitted_at":"2023-10-12T08:22:37Z","abstract_excerpt":"There have been widespread claims about Large Language Models (LLMs) being able to successfully verify or self-critique their candidate solutions in reasoning problems in an iterative mode. Intrigued by those claims, in this paper we set out to investigate the verification/self-critiquing abilities of large language models in the context of planning. We evaluate a planning system that employs LLMs for both plan generation and verification. We assess the verifier LLM's performance against ground-truth verification, the impact of self-critiquing on plan generation, and the influence of varying f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08118","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/2310.08118/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":"2310.08118","created_at":"2026-07-05T07:00:10.328112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08118v1","created_at":"2026-07-05T07:00:10.328112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08118","created_at":"2026-07-05T07:00:10.328112+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXBLHR3DXLCG","created_at":"2026-07-05T07:00:10.328112+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXBLHR3DXLCGZYK6","created_at":"2026-07-05T07:00:10.328112+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXBLHR3D","created_at":"2026-07-05T07:00:10.328112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31511","citing_title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14636","citing_title":"Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26745","citing_title":"Deep sequence models tend to memorize geometrically; it is unclear why","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16941","citing_title":"Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09629","citing_title":"End-to-end PDDL Planning with Hardcoded and Dynamic Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":232,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X","json":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X.json","graph_json":"https://pith.science/api/pith-number/KXBLHR3DXLCGZYK6LGHIN47P2X/graph.json","events_json":"https://pith.science/api/pith-number/KXBLHR3DXLCGZYK6LGHIN47P2X/events.json","paper":"https://pith.science/paper/KXBLHR3D"},"agent_actions":{"view_html":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X","download_json":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X.json","view_paper":"https://pith.science/paper/KXBLHR3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08118&json=true","fetch_graph":"https://pith.science/api/pith-number/KXBLHR3DXLCGZYK6LGHIN47P2X/graph.json","fetch_events":"https://pith.science/api/pith-number/KXBLHR3DXLCGZYK6LGHIN47P2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X/action/storage_attestation","attest_author":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X/action/author_attestation","sign_citation":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X/action/citation_signature","submit_replication":"https://pith.science/pith/KXBLHR3DXLCGZYK6LGHIN47P2X/action/replication_record"}},"created_at":"2026-07-05T07:00:10.328112+00:00","updated_at":"2026-07-05T07:00:10.328112+00:00"}