{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JFLOZ5SO6Y3F3SSYHSLNNL5DX2","short_pith_number":"pith:JFLOZ5SO","schema_version":"1.0","canonical_sha256":"4956ecf64ef6365dca583c96d6afa3beadb3c5278e50069185403f8695b28735","source":{"kind":"arxiv","id":"2311.07582","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Potential of Leading Large Language Models in Reasoning Biology Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongtu Zhu, Jason Holmes, Jianli Zhang, Qi Gan, Tian Jiang, Tianming Liu, Wei Liu, Xinyu Gong, Yajun Yan, Yiwei Li, Yusong Zou, Yuxi Teng, Zhengliang Liu, Zihao Wu","submitted_at":"2023-11-05T03:34:17Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have presented new opportunities for integrating Artificial General Intelligence (AGI) into biological research and education. This study evaluated the capabilities of leading LLMs, including GPT-4, GPT-3.5, PaLM2, Claude2, and SenseNova, in answering conceptual biology questions. The models were tested on a 108-question multiple-choice exam covering biology topics in molecular biology, biological techniques, metabolic engineering, and synthetic biology. Among the models, GPT-4 achieved the highest average score of 90 and demonstrated the greates"},"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":"2311.07582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-05T03:34:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a7abb6ed73e4328d675cceaccab01893405fb4f68b4f955e15f5cb18e5a6b3c5","abstract_canon_sha256":"f6004c47a5972a85d7959fea7b86f90a22e3c5802432aa8288c0a9b26a5d06c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:20.718415Z","signature_b64":"AN5jvp0ZCYSsjjkqcwg9CxASj83hlbO4Sgxl5f45gY1zZWJFBWbpAlBE07zQvGt5wBSJbsbcHMsu0OPNgWsOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4956ecf64ef6365dca583c96d6afa3beadb3c5278e50069185403f8695b28735","last_reissued_at":"2026-07-05T07:12:20.717924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:20.717924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Potential of Leading Large Language Models in Reasoning Biology Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongtu Zhu, Jason Holmes, Jianli Zhang, Qi Gan, Tian Jiang, Tianming Liu, Wei Liu, Xinyu Gong, Yajun Yan, Yiwei Li, Yusong Zou, Yuxi Teng, Zhengliang Liu, Zihao Wu","submitted_at":"2023-11-05T03:34:17Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have presented new opportunities for integrating Artificial General Intelligence (AGI) into biological research and education. This study evaluated the capabilities of leading LLMs, including GPT-4, GPT-3.5, PaLM2, Claude2, and SenseNova, in answering conceptual biology questions. The models were tested on a 108-question multiple-choice exam covering biology topics in molecular biology, biological techniques, metabolic engineering, and synthetic biology. Among the models, GPT-4 achieved the highest average score of 90 and demonstrated the greates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07582","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/2311.07582/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":"2311.07582","created_at":"2026-07-05T07:12:20.717986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07582v1","created_at":"2026-07-05T07:12:20.717986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07582","created_at":"2026-07-05T07:12:20.717986+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFLOZ5SO6Y3F","created_at":"2026-07-05T07:12:20.717986+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFLOZ5SO6Y3F3SSY","created_at":"2026-07-05T07:12:20.717986+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFLOZ5SO","created_at":"2026-07-05T07:12:20.717986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2","json":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2.json","graph_json":"https://pith.science/api/pith-number/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/graph.json","events_json":"https://pith.science/api/pith-number/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/events.json","paper":"https://pith.science/paper/JFLOZ5SO"},"agent_actions":{"view_html":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2","download_json":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2.json","view_paper":"https://pith.science/paper/JFLOZ5SO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07582&json=true","fetch_graph":"https://pith.science/api/pith-number/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/graph.json","fetch_events":"https://pith.science/api/pith-number/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/action/storage_attestation","attest_author":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/action/author_attestation","sign_citation":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/action/citation_signature","submit_replication":"https://pith.science/pith/JFLOZ5SO6Y3F3SSYHSLNNL5DX2/action/replication_record"}},"created_at":"2026-07-05T07:12:20.717986+00:00","updated_at":"2026-07-05T07:12:20.717986+00:00"}