{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:25HBGA6PBM37FRX4RWYJ2L4S5X","short_pith_number":"pith:25HBGA6P","schema_version":"1.0","canonical_sha256":"d74e1303cf0b37f2c6fc8db09d2f92edf9918e1a926f46aad61579acbd9c95bb","source":{"kind":"arxiv","id":"2308.03762","version":2},"attestation_state":"computed","paper":{"title":"GPT-4 Can't Reason","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Konstantine Arkoudas","submitted_at":"2023-07-21T17:04:25Z","abstract_excerpt":"GPT-4 was released in March 2023 to wide acclaim, marking a very substantial improvement across the board over GPT-3.5 (OpenAI's previously best model, which had powered the initial release of ChatGPT). However, despite the genuinely impressive improvement, there are good reasons to be highly skeptical of GPT-4's ability to reason. This position paper discusses the nature of reasoning; criticizes the current formulation of reasoning problems in the NLP community, as well as the way in which LLM reasoning performance is currently evaluated; introduces a small collection of 21 diverse reasoning "},"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":"2308.03762","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-21T17:04:25Z","cross_cats_sorted":[],"title_canon_sha256":"8d1f56b94309d050011942429359ff407b02a1e40bd5dfea59ef4207588953f0","abstract_canon_sha256":"14035c156715923f4f0afd7876e741bf8325d4f9c08b5cea3441e0974b2e173f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:55.212890Z","signature_b64":"L5T+OoqVUdVbxsEOxGOTpFu1BeD0l9cm0irEOiYM6FTxKcUpMcJ3egGsUhe5M1i4mdA8zsAIejLLUeMxjXySDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d74e1303cf0b37f2c6fc8db09d2f92edf9918e1a926f46aad61579acbd9c95bb","last_reissued_at":"2026-07-05T06:39:55.212482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:55.212482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT-4 Can't Reason","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Konstantine Arkoudas","submitted_at":"2023-07-21T17:04:25Z","abstract_excerpt":"GPT-4 was released in March 2023 to wide acclaim, marking a very substantial improvement across the board over GPT-3.5 (OpenAI's previously best model, which had powered the initial release of ChatGPT). However, despite the genuinely impressive improvement, there are good reasons to be highly skeptical of GPT-4's ability to reason. This position paper discusses the nature of reasoning; criticizes the current formulation of reasoning problems in the NLP community, as well as the way in which LLM reasoning performance is currently evaluated; introduces a small collection of 21 diverse reasoning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.03762","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/2308.03762/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":"2308.03762","created_at":"2026-07-05T06:39:55.212548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.03762v2","created_at":"2026-07-05T06:39:55.212548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.03762","created_at":"2026-07-05T06:39:55.212548+00:00"},{"alias_kind":"pith_short_12","alias_value":"25HBGA6PBM37","created_at":"2026-07-05T06:39:55.212548+00:00"},{"alias_kind":"pith_short_16","alias_value":"25HBGA6PBM37FRX4","created_at":"2026-07-05T06:39:55.212548+00:00"},{"alias_kind":"pith_short_8","alias_value":"25HBGA6P","created_at":"2026-07-05T06:39:55.212548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13607","citing_title":"Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X","json":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X.json","graph_json":"https://pith.science/api/pith-number/25HBGA6PBM37FRX4RWYJ2L4S5X/graph.json","events_json":"https://pith.science/api/pith-number/25HBGA6PBM37FRX4RWYJ2L4S5X/events.json","paper":"https://pith.science/paper/25HBGA6P"},"agent_actions":{"view_html":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X","download_json":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X.json","view_paper":"https://pith.science/paper/25HBGA6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.03762&json=true","fetch_graph":"https://pith.science/api/pith-number/25HBGA6PBM37FRX4RWYJ2L4S5X/graph.json","fetch_events":"https://pith.science/api/pith-number/25HBGA6PBM37FRX4RWYJ2L4S5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X/action/storage_attestation","attest_author":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X/action/author_attestation","sign_citation":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X/action/citation_signature","submit_replication":"https://pith.science/pith/25HBGA6PBM37FRX4RWYJ2L4S5X/action/replication_record"}},"created_at":"2026-07-05T06:39:55.212548+00:00","updated_at":"2026-07-05T06:39:55.212548+00:00"}