{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GJ5ZXOBDKNT5S3RH764SY4OIRP","short_pith_number":"pith:GJ5ZXOBD","schema_version":"1.0","canonical_sha256":"327b9bb8235367d96e27ffb92c71c88bd10ae7212babaff1f333548eab13265c","source":{"kind":"arxiv","id":"2412.05753","version":1},"attestation_state":"computed","paper":{"title":"Can OpenAI o1 outperform humans in higher-order cognitive thinking?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Arne Bewerdorff, Ehsan Latif, Lehong Shi, Matthew Nyaaba, Shuchen Guo, Xiantong Yang, Xiaoming Zhai, Yifan Zhou, Yizhu Gao","submitted_at":"2024-12-07T21:52:03Z","abstract_excerpt":"This study evaluates the performance of OpenAI's o1-preview model in higher-order cognitive domains, including critical thinking, systematic thinking, computational thinking, data literacy, creative thinking, logical reasoning, and scientific reasoning. Using established benchmarks, we compared the o1-preview models's performance to human participants from diverse educational levels. o1-preview achieved a mean score of 24.33 on the Ennis-Weir Critical Thinking Essay Test (EWCTET), surpassing undergraduate (13.8) and postgraduate (18.39) participants (z = 1.60 and 0.90, respectively). In system"},"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":"2412.05753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2024-12-07T21:52:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c309a8df97f645d541d3e33b006fc5a5bc07c3ed459e810494788e590634d68","abstract_canon_sha256":"0eb0ca73acff13f635137a6ad72e15c5a0a16f668020d2dea7d15def0e41da9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:08.304958Z","signature_b64":"3EZBfB/mprJk+0o8dw4rzik2hKAeJ0kmIjKWmrDnMyVtjUoDsALqIS2KKg3+F0gqSjDRh+4uZ3zSYhDJi7H4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"327b9bb8235367d96e27ffb92c71c88bd10ae7212babaff1f333548eab13265c","last_reissued_at":"2026-07-05T09:46:08.304296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:08.304296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can OpenAI o1 outperform humans in higher-order cognitive thinking?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Arne Bewerdorff, Ehsan Latif, Lehong Shi, Matthew Nyaaba, Shuchen Guo, Xiantong Yang, Xiaoming Zhai, Yifan Zhou, Yizhu Gao","submitted_at":"2024-12-07T21:52:03Z","abstract_excerpt":"This study evaluates the performance of OpenAI's o1-preview model in higher-order cognitive domains, including critical thinking, systematic thinking, computational thinking, data literacy, creative thinking, logical reasoning, and scientific reasoning. Using established benchmarks, we compared the o1-preview models's performance to human participants from diverse educational levels. o1-preview achieved a mean score of 24.33 on the Ennis-Weir Critical Thinking Essay Test (EWCTET), surpassing undergraduate (13.8) and postgraduate (18.39) participants (z = 1.60 and 0.90, respectively). In system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05753","kind":"arxiv","version":1},"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/2412.05753/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":"2412.05753","created_at":"2026-07-05T09:46:08.304387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05753v1","created_at":"2026-07-05T09:46:08.304387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05753","created_at":"2026-07-05T09:46:08.304387+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJ5ZXOBDKNT5","created_at":"2026-07-05T09:46:08.304387+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJ5ZXOBDKNT5S3RH","created_at":"2026-07-05T09:46:08.304387+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJ5ZXOBD","created_at":"2026-07-05T09:46:08.304387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18759","citing_title":"Interoceptive Divergence in Aesthetic Evaluation and Implications for Human-AI Alignment","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP","json":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP.json","graph_json":"https://pith.science/api/pith-number/GJ5ZXOBDKNT5S3RH764SY4OIRP/graph.json","events_json":"https://pith.science/api/pith-number/GJ5ZXOBDKNT5S3RH764SY4OIRP/events.json","paper":"https://pith.science/paper/GJ5ZXOBD"},"agent_actions":{"view_html":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP","download_json":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP.json","view_paper":"https://pith.science/paper/GJ5ZXOBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05753&json=true","fetch_graph":"https://pith.science/api/pith-number/GJ5ZXOBDKNT5S3RH764SY4OIRP/graph.json","fetch_events":"https://pith.science/api/pith-number/GJ5ZXOBDKNT5S3RH764SY4OIRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP/action/storage_attestation","attest_author":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP/action/author_attestation","sign_citation":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP/action/citation_signature","submit_replication":"https://pith.science/pith/GJ5ZXOBDKNT5S3RH764SY4OIRP/action/replication_record"}},"created_at":"2026-07-05T09:46:08.304387+00:00","updated_at":"2026-07-05T09:46:08.304387+00:00"}