{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SFXOPLFLVDJI3U34ZYAT2UXKP2","short_pith_number":"pith:SFXOPLFL","schema_version":"1.0","canonical_sha256":"916ee7acaba8d28dd37cce013d52ea7ebb2b68360f00ea19e86534f50cd0e3d2","source":{"kind":"arxiv","id":"2507.08144","version":1},"attestation_state":"computed","paper":{"title":"AI for NONMEM Coding in Pharmacometrics Research and Education: Shortcut or Pitfall?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.OT","authors_text":"Carl M.J. Kirkpatrick, Cornelia B. Landersdorfer, Huaxiu Yao, Jiawei Zhou, Wanbing Wang, Wenhao Zheng","submitted_at":"2025-07-10T20:05:35Z","abstract_excerpt":"Artificial intelligence (AI) is increasingly being explored as a tool to support pharmacometric modeling, particularly in addressing the coding challenges associated with NONMEM. In this study, we evaluated the ability of seven AI agents to generate NONMEM codes across 13 pharmacometrics tasks, including a range of population pharmacokinetic (PK) and pharmacodynamic (PD) models. We further developed a standardized scoring rubric to assess code accuracy and created an optimized prompt to improve AI agent performance. Our results showed that the OpenAI o1 and gpt-4.1 models achieved the best per"},"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":"2507.08144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.OT","submitted_at":"2025-07-10T20:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"b3ef4602674a3e37af319cc39f8ced3636aa19aacc7bc322573a8267dfb5ab3b","abstract_canon_sha256":"4ea0bbffd454bcb788ce5a489661ae8dfbd4cbc3e832ed93f567e97fbfa5b5ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:17.906479Z","signature_b64":"Q7ywOJvnrRTseIDoKcr9meFtRuJOnI3CXvOADzF3uBJaMkEWyjadUefh57oydvGPpEVw8wE7cRrdMtOvmb4oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"916ee7acaba8d28dd37cce013d52ea7ebb2b68360f00ea19e86534f50cd0e3d2","last_reissued_at":"2026-07-05T11:35:17.905948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:17.905948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI for NONMEM Coding in Pharmacometrics Research and Education: Shortcut or Pitfall?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.OT","authors_text":"Carl M.J. Kirkpatrick, Cornelia B. Landersdorfer, Huaxiu Yao, Jiawei Zhou, Wanbing Wang, Wenhao Zheng","submitted_at":"2025-07-10T20:05:35Z","abstract_excerpt":"Artificial intelligence (AI) is increasingly being explored as a tool to support pharmacometric modeling, particularly in addressing the coding challenges associated with NONMEM. In this study, we evaluated the ability of seven AI agents to generate NONMEM codes across 13 pharmacometrics tasks, including a range of population pharmacokinetic (PK) and pharmacodynamic (PD) models. We further developed a standardized scoring rubric to assess code accuracy and created an optimized prompt to improve AI agent performance. Our results showed that the OpenAI o1 and gpt-4.1 models achieved the best per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08144","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/2507.08144/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":"2507.08144","created_at":"2026-07-05T11:35:17.906013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08144v1","created_at":"2026-07-05T11:35:17.906013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08144","created_at":"2026-07-05T11:35:17.906013+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFXOPLFLVDJI","created_at":"2026-07-05T11:35:17.906013+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFXOPLFLVDJI3U34","created_at":"2026-07-05T11:35:17.906013+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFXOPLFL","created_at":"2026-07-05T11:35:17.906013+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/SFXOPLFLVDJI3U34ZYAT2UXKP2","json":"https://pith.science/pith/SFXOPLFLVDJI3U34ZYAT2UXKP2.json","graph_json":"https://pith.science/api/pith-number/SFXOPLFLVDJI3U34ZYAT2UXKP2/graph.json","events_json":"https://pith.science/api/pith-number/SFXOPLFLVDJI3U34ZYAT2UXKP2/events.json","paper":"https://pith.science/paper/SFXOPLFL"},"agent_actions":{"view_html":"https://pith.science/pith/SFXOPLFLVDJI3U34ZYAT2UXKP2","download_json":"https://pith.science/pith/SFXOPLFLVDJI3U34ZYAT2UXKP2.json","view_paper":"https://pith.science/paper/SFXOPLFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08144&json=true","fetch_graph":"https://pith.science/api/pith-number/SFXOPLFLVDJI3U34ZYAT2UXKP2/graph.json","fetch_events":"https://pith.science/api/pith-number/SFXOPLFLVDJI3U34ZYAT2UXKP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFXOPLFLVDJI3U34ZYAT2UXKP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFXOPLFLVDJI3U34ZYAT2UXKP2/action/storage_attestation","attest_author":"https://pith.science/pith/SFXOPLFLVDJI3U34ZYAT2UXKP2/action/author_attestation","sign_citation":"https://pith.science/pith/SFXOPLFLVDJI3U34ZYAT2UXKP2/action/citation_signature","submit_replication":"https://pith.science/pith/SFXOPLFLVDJI3U34ZYAT2UXKP2/action/replication_record"}},"created_at":"2026-07-05T11:35:17.906013+00:00","updated_at":"2026-07-05T11:35:17.906013+00:00"}