{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GUX4OV6HJEGEK7RBPKNF57WT2F","short_pith_number":"pith:GUX4OV6H","schema_version":"1.0","canonical_sha256":"352fc757c7490c457e217a9a5efed3d142162f38057a7afe89b0bfe54f9e8846","source":{"kind":"arxiv","id":"2305.15771","version":2},"attestation_state":"computed","paper":{"title":"On the Planning Abilities of Large Language Models : A Critical Investigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, Subbarao Kambhampati","submitted_at":"2023-05-25T06:32:23Z","abstract_excerpt":"Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs in LLM-Modulo settings where they act as a source of heuristic guidance for external planners and verifiers. We conduct a systematic study by generating a suite of instances on domains similar to the ones employed in the International Planning Competition and evaluate LLMs in two distinct"},"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":"2305.15771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-25T06:32:23Z","cross_cats_sorted":[],"title_canon_sha256":"0454a1427fe5e23fe62f3b7e80da2823ab657defb0cf03970246d87ded20f370","abstract_canon_sha256":"34a6eee49a0f2d8674c894fa6b56b4a2cea6ed8b5e14c892d0cc892a1a0bd9dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:55.366971Z","signature_b64":"3j2EQSfX0wkM82qsdkEeXbUJQvfsSXFmmENYwL8QgvGbcSP+NRnXJoc0TxLDapvx6n9ipnx7C6AGir/PW+KLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"352fc757c7490c457e217a9a5efed3d142162f38057a7afe89b0bfe54f9e8846","last_reissued_at":"2026-07-05T07:15:55.366264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:55.366264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Planning Abilities of Large Language Models : A Critical Investigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, Subbarao Kambhampati","submitted_at":"2023-05-25T06:32:23Z","abstract_excerpt":"Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs in LLM-Modulo settings where they act as a source of heuristic guidance for external planners and verifiers. We conduct a systematic study by generating a suite of instances on domains similar to the ones employed in the International Planning Competition and evaluate LLMs in two distinct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15771","kind":"arxiv","version":2},"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/2305.15771/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":"2305.15771","created_at":"2026-07-05T07:15:55.366355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15771v2","created_at":"2026-07-05T07:15:55.366355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15771","created_at":"2026-07-05T07:15:55.366355+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUX4OV6HJEGE","created_at":"2026-07-05T07:15:55.366355+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUX4OV6HJEGEK7RB","created_at":"2026-07-05T07:15:55.366355+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUX4OV6H","created_at":"2026-07-05T07:15:55.366355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26525","citing_title":"ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30052","citing_title":"REPOT: Recoverable Program-of-Thought via Checkpoint Repair","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2304.11477","citing_title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F","json":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F.json","graph_json":"https://pith.science/api/pith-number/GUX4OV6HJEGEK7RBPKNF57WT2F/graph.json","events_json":"https://pith.science/api/pith-number/GUX4OV6HJEGEK7RBPKNF57WT2F/events.json","paper":"https://pith.science/paper/GUX4OV6H"},"agent_actions":{"view_html":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F","download_json":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F.json","view_paper":"https://pith.science/paper/GUX4OV6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15771&json=true","fetch_graph":"https://pith.science/api/pith-number/GUX4OV6HJEGEK7RBPKNF57WT2F/graph.json","fetch_events":"https://pith.science/api/pith-number/GUX4OV6HJEGEK7RBPKNF57WT2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F/action/storage_attestation","attest_author":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F/action/author_attestation","sign_citation":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F/action/citation_signature","submit_replication":"https://pith.science/pith/GUX4OV6HJEGEK7RBPKNF57WT2F/action/replication_record"}},"created_at":"2026-07-05T07:15:55.366355+00:00","updated_at":"2026-07-05T07:15:55.366355+00:00"}