{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IPYWYWZNEXD6KOCEN75QMJRWLV","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":"c47da14821bde0eae13c996f477c47ee02966b4805a9e0a06047bc4edec57d10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T23:11:01Z","title_canon_sha256":"674f1e1476399bb83c22ff4681988349cbd8343de91f6cea0b35b42dbc3debad"},"schema_version":"1.0","source":{"id":"2402.08115","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08115","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08115v2","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08115","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"IPYWYWZNEXD6","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"IPYWYWZNEXD6KOCE","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"IPYWYWZN","created_at":"2026-07-05T08:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:d3473621e485502ca01136353a14a6bc791764b1d6a781d620ebcb86091b2bef","target":"graph","created_at":"2026-07-05T08:51:47Z","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/2402.08115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been considerable divergence of opinion on the reasoning abilities of Large Language Models (LLMs). While the initial optimism that reasoning might emerge automatically with scale has been tempered thanks to a slew of counterexamples--ranging from multiplication to simple planning--there persists a wide spread belief that LLMs can self-critique and improve their own solutions in an iterative fashion. This belief seemingly rests on the assumption that verification of correctness should be easier than generation--a rather classical argument from computational complexity--which should b","authors_text":"Karthik Valmeekam, Kaya Stechly, Subbarao Kambhampati","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T23:11:01Z","title":"On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08115","kind":"arxiv","version":2},"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:fbf2b396173dc408942ab2822c9903c94099feefe3a47b8d9999a47f5c8f3725","target":"record","created_at":"2026-07-05T08:51:47Z","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":"c47da14821bde0eae13c996f477c47ee02966b4805a9e0a06047bc4edec57d10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T23:11:01Z","title_canon_sha256":"674f1e1476399bb83c22ff4681988349cbd8343de91f6cea0b35b42dbc3debad"},"schema_version":"1.0","source":{"id":"2402.08115","kind":"arxiv","version":2}},"canonical_sha256":"43f16c5b2d25c7e538446ffb0626365d5cd7ad88c663f68d166823e06c25c119","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43f16c5b2d25c7e538446ffb0626365d5cd7ad88c663f68d166823e06c25c119","first_computed_at":"2026-07-05T08:51:47.146704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:47.146704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oNIebHL0NdlC1RdL315uYQczYm7SMOfmrKaHv10azjw/L3sWcmedR959PRxeLEXQCXUA6+OMhkV9EPTc8lVEDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:47.147146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08115","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbf2b396173dc408942ab2822c9903c94099feefe3a47b8d9999a47f5c8f3725","sha256:d3473621e485502ca01136353a14a6bc791764b1d6a781d620ebcb86091b2bef"],"state_sha256":"5ea94606a5403525dc1ad306ff35bc50bad4c124c4e10d1aed6cd3eb220495e1"}