{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TTAVJK6XF3ULDWTGUNWAMERCZE","short_pith_number":"pith:TTAVJK6X","schema_version":"1.0","canonical_sha256":"9cc154abd72ee8b1da66a36c061222c9079becc00dbcd7cb147d3e925e948259","source":{"kind":"arxiv","id":"2405.04776","version":3},"attestation_state":"computed","paper":{"title":"Chain of Thoughtlessness? An Analysis of CoT in Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Karthik Valmeekam, Kaya Stechly, Subbarao Kambhampati","submitted_at":"2024-05-08T02:48:28Z","abstract_excerpt":"Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution procedures-with the intuition that it is possible to in-context teach an LLM an algorithm for solving the problem. This paper presents a case study of chain of thought on problems from Blocksworld, a classical planning domain, and examines the performance of two state-of-the-art LLMs across two axes: generality of examples given in prompt, and complexity of problems"},"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":"2405.04776","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-08T02:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"d942bce9f9ae894c6b98c44d876e4d1d497bb09ff40a102c33fbc71a940a56c9","abstract_canon_sha256":"7690bd485886df676f3236ef7d7848cf647f8e0bd855e763466060d8df7a7185"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:17.010372Z","signature_b64":"t1N9ltc63+7pU5nIaDSmuHr4rJ9AqUYfoRiGgSHJmmnm8lwEI5hXQavhDmrTFZmH0n/TgnI/9gmsKmKBTRmhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc154abd72ee8b1da66a36c061222c9079becc00dbcd7cb147d3e925e948259","last_reissued_at":"2026-07-05T10:29:17.009614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:17.009614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain of Thoughtlessness? An Analysis of CoT in Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Karthik Valmeekam, Kaya Stechly, Subbarao Kambhampati","submitted_at":"2024-05-08T02:48:28Z","abstract_excerpt":"Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution procedures-with the intuition that it is possible to in-context teach an LLM an algorithm for solving the problem. This paper presents a case study of chain of thought on problems from Blocksworld, a classical planning domain, and examines the performance of two state-of-the-art LLMs across two axes: generality of examples given in prompt, and complexity of problems"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04776","kind":"arxiv","version":3},"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/2405.04776/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":"2405.04776","created_at":"2026-07-05T10:29:17.009704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04776v3","created_at":"2026-07-05T10:29:17.009704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04776","created_at":"2026-07-05T10:29:17.009704+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTAVJK6XF3UL","created_at":"2026-07-05T10:29:17.009704+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTAVJK6XF3ULDWTG","created_at":"2026-07-05T10:29:17.009704+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTAVJK6X","created_at":"2026-07-05T10:29:17.009704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07632","citing_title":"From Custom-Fit to Portable: Bridging the Gap Between Synthesized and Engineered GPU Query Execution","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21740","citing_title":"Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03503","citing_title":"ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06040","citing_title":"Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07776","citing_title":"Tracing Uncertainty in Language Model \"Reasoning\"","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE","json":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE.json","graph_json":"https://pith.science/api/pith-number/TTAVJK6XF3ULDWTGUNWAMERCZE/graph.json","events_json":"https://pith.science/api/pith-number/TTAVJK6XF3ULDWTGUNWAMERCZE/events.json","paper":"https://pith.science/paper/TTAVJK6X"},"agent_actions":{"view_html":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE","download_json":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE.json","view_paper":"https://pith.science/paper/TTAVJK6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04776&json=true","fetch_graph":"https://pith.science/api/pith-number/TTAVJK6XF3ULDWTGUNWAMERCZE/graph.json","fetch_events":"https://pith.science/api/pith-number/TTAVJK6XF3ULDWTGUNWAMERCZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE/action/storage_attestation","attest_author":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE/action/author_attestation","sign_citation":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE/action/citation_signature","submit_replication":"https://pith.science/pith/TTAVJK6XF3ULDWTGUNWAMERCZE/action/replication_record"}},"created_at":"2026-07-05T10:29:17.009704+00:00","updated_at":"2026-07-05T10:29:17.009704+00:00"}