{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4WGSU6KFA6IVCTISABL4DCS6NG","short_pith_number":"pith:4WGSU6KF","schema_version":"1.0","canonical_sha256":"e58d2a79450791514d120057c18a5e6984037379c2c185420c7ec3cceabdd5c9","source":{"kind":"arxiv","id":"2311.09247","version":3},"attestation_state":"computed","paper":{"title":"Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessandro B. Palmarini, Arseny Moskvichev, Melanie Mitchell","submitted_at":"2023-11-14T04:33:49Z","abstract_excerpt":"We explore the abstract reasoning abilities of text-only and multimodal versions of GPT-4, using the ConceptARC benchmark [10], which is designed to evaluate robust understanding and reasoning with core-knowledge concepts. We extend the work of Moskvichev et al. [10] by evaluating GPT-4 on more detailed, one-shot prompting (rather than simple, zero-shot prompts) with text versions of ConceptARC tasks, and by evaluating GPT-4V, the multimodal version of GPT-4, on zero- and one-shot prompts using image versions of the simplest tasks. Our experimental results support the conclusion that neither v"},"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":"2311.09247","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-11-14T04:33:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d92410a6b4d69dada6237bd0bce5e94ee8e0cd497f69d2f69b410fc5adb39767","abstract_canon_sha256":"188f11baab2830c0b5039a89e743bf74120d10e19abd2ffbde2f94462ba85c18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:09.395791Z","signature_b64":"e8uU++ZR7Z8Y/JKpBDknKVzMm0axfv0NhMtgjcK1eVLNIWHLxAbRtfh++HXBnLUyVt9LE1V2ABD1sQptR+2wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e58d2a79450791514d120057c18a5e6984037379c2c185420c7ec3cceabdd5c9","last_reissued_at":"2026-07-05T07:27:09.395376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:09.395376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessandro B. Palmarini, Arseny Moskvichev, Melanie Mitchell","submitted_at":"2023-11-14T04:33:49Z","abstract_excerpt":"We explore the abstract reasoning abilities of text-only and multimodal versions of GPT-4, using the ConceptARC benchmark [10], which is designed to evaluate robust understanding and reasoning with core-knowledge concepts. We extend the work of Moskvichev et al. [10] by evaluating GPT-4 on more detailed, one-shot prompting (rather than simple, zero-shot prompts) with text versions of ConceptARC tasks, and by evaluating GPT-4V, the multimodal version of GPT-4, on zero- and one-shot prompts using image versions of the simplest tasks. Our experimental results support the conclusion that neither v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09247","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/2311.09247/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":"2311.09247","created_at":"2026-07-05T07:27:09.395433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09247v3","created_at":"2026-07-05T07:27:09.395433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09247","created_at":"2026-07-05T07:27:09.395433+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WGSU6KFA6IV","created_at":"2026-07-05T07:27:09.395433+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WGSU6KFA6IVCTIS","created_at":"2026-07-05T07:27:09.395433+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WGSU6KF","created_at":"2026-07-05T07:27:09.395433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23141","citing_title":"VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18907","citing_title":"Gradient-Based Program Synthesis with Neurally Interpreted Languages","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG","json":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG.json","graph_json":"https://pith.science/api/pith-number/4WGSU6KFA6IVCTISABL4DCS6NG/graph.json","events_json":"https://pith.science/api/pith-number/4WGSU6KFA6IVCTISABL4DCS6NG/events.json","paper":"https://pith.science/paper/4WGSU6KF"},"agent_actions":{"view_html":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG","download_json":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG.json","view_paper":"https://pith.science/paper/4WGSU6KF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09247&json=true","fetch_graph":"https://pith.science/api/pith-number/4WGSU6KFA6IVCTISABL4DCS6NG/graph.json","fetch_events":"https://pith.science/api/pith-number/4WGSU6KFA6IVCTISABL4DCS6NG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG/action/storage_attestation","attest_author":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG/action/author_attestation","sign_citation":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG/action/citation_signature","submit_replication":"https://pith.science/pith/4WGSU6KFA6IVCTISABL4DCS6NG/action/replication_record"}},"created_at":"2026-07-05T07:27:09.395433+00:00","updated_at":"2026-07-05T07:27:09.395433+00:00"}