{"id":"W4403091357","doi":"10.1039/d4dd00248b","title":"Leveraging GPT-4 to transform chemistry from paper to practice","year":2024,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Structural Genomics Consortium; University of Toronto; University of British Columbia","funders":"Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Canada Foundation for Innovation","keywords":"Chemistry; Computer science; Data science; Computational biology; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00100542,0.0001512326,0.0001591066,0.0001316785,0.00009389542,0.0110892,0.0008432084,0.00002809825,0.0003172595],"category_scores_gemma":[0.002673599,0.0001146165,0.0001244925,0.001063912,0.0000257845,0.004392917,0.0004891091,0.0001030734,0.004373493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006995648,"about_ca_system_score_gemma":0.00007437559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007173059,"about_ca_topic_score_gemma":0.000005626721,"domain_scores_codex":[0.9969607,0.00001689785,0.0004062654,0.001027454,0.001294866,0.000293843],"domain_scores_gemma":[0.9976714,0.001148857,0.00003070659,0.0008731829,0.00007011416,0.0002057868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004779077,0.00007880497,0.00006950293,0.00001161995,0.00004580726,0.0001125405,0.002349915,0.0009053023,0.001451083,0.0006274661,0.4061564,0.5881438],"study_design_scores_gemma":[0.00005982519,0.00001561532,0.0004235489,0.00007190391,0.00001052648,0.000004389587,0.002451053,0.0006845676,0.000695565,0.006970273,0.9884152,0.0001975372],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.325257,0.0002876531,0.2559809,0.02569062,0.004464325,0.0003785549,0.001064232,0.0003140338,0.3865627],"genre_scores_gemma":[0.9537743,0.000001596867,0.0006198491,0.002225073,0.0002249198,0.000009348131,0.00007206142,0.00001426085,0.04305862],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6285173,"threshold_uncertainty_score":0.9964017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05411526277582506,"score_gpt":0.3571359091403664,"score_spread":0.3030206463645413,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}