{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KXBLHR3DXLCGZYK6LGHIN47P2X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7e2901d8293721d5c65c4cfbf6f268e4355e26570f2f0841ff5662ca54d7b4ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T08:22:37Z","title_canon_sha256":"7af771630f642e56a4ccdf38c174a6efb4f2946fab383775d137525fde68f4f7"},"schema_version":"1.0","source":{"id":"2310.08118","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08118","created_at":"2026-07-05T07:00:10Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08118v1","created_at":"2026-07-05T07:00:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08118","created_at":"2026-07-05T07:00:10Z"},{"alias_kind":"pith_short_12","alias_value":"KXBLHR3DXLCG","created_at":"2026-07-05T07:00:10Z"},{"alias_kind":"pith_short_16","alias_value":"KXBLHR3DXLCGZYK6","created_at":"2026-07-05T07:00:10Z"},{"alias_kind":"pith_short_8","alias_value":"KXBLHR3D","created_at":"2026-07-05T07:00:10Z"}],"graph_snapshots":[{"event_id":"sha256:84b38a549f3fe901b1166e466cdc0156edbc892931c072b5eb2eb02878af6fff","target":"graph","created_at":"2026-07-05T07:00:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.08118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Karthik Valmeekam, Matthew Marquez, Subbarao Kambhampati","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T08:22:37Z","title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08118","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f7f147b620ae004db1c07e896b93e1f8215e1ddad7f6fee41491237c2a964d66","target":"record","created_at":"2026-07-05T07:00:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7e2901d8293721d5c65c4cfbf6f268e4355e26570f2f0841ff5662ca54d7b4ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T08:22:37Z","title_canon_sha256":"7af771630f642e56a4ccdf38c174a6efb4f2946fab383775d137525fde68f4f7"},"schema_version":"1.0","source":{"id":"2310.08118","kind":"arxiv","version":1}},"canonical_sha256":"55c2b3c763bac46ce15e598e86f3efd5f5f1ade37dfc05757bbd9b8918282771","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55c2b3c763bac46ce15e598e86f3efd5f5f1ade37dfc05757bbd9b8918282771","first_computed_at":"2026-07-05T07:00:10.328055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:10.328055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cb4R1hxJnNENlzpulIfT9T+5oScjVcF4TXKGau2dGg5S1RdTVimDCFWuY1MbfEg+gETe8GjWWZNv7gEcdCRZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:10.328540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08118","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7f147b620ae004db1c07e896b93e1f8215e1ddad7f6fee41491237c2a964d66","sha256:84b38a549f3fe901b1166e466cdc0156edbc892931c072b5eb2eb02878af6fff"],"state_sha256":"e4f8fb9b9b9f3ecec8a2c20fe35121b2964412a9d0b8e7dc44a0f52715878136"}