{"id":"W4400046055","doi":"10.1186/s12859-024-05847-x","title":"Can large language models understand molecules?","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cheminformatics; Computer science; Embedding; Representation (politics); Artificial intelligence; Natural language processing; Field (mathematics); Property (philosophy); Machine learning; Bioinformatics; Biology; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009210319,0.000183034,0.0001777482,0.0001222596,0.0001557544,0.0006930692,0.0004398023,0.00007953495,0.0007745451],"category_scores_gemma":[0.00009742816,0.0001457171,0.00005955797,0.0002625846,0.0001016703,0.0006004175,0.0001876879,0.0001363484,0.001108233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008610018,"about_ca_system_score_gemma":0.0001711132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006029824,"about_ca_topic_score_gemma":0.00008884422,"domain_scores_codex":[0.9984193,0.00006010613,0.0003858479,0.0002151494,0.0004457496,0.0004738164],"domain_scores_gemma":[0.9992787,0.00009352875,0.00008198748,0.0003971609,0.00003120684,0.0001174007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006707508,0.0001547262,0.0002825594,0.005407206,0.00003698348,0.0001585156,0.08022007,0.2830872,0.1529754,0.4540909,0.02120752,0.002311769],"study_design_scores_gemma":[0.0001367465,0.00003093956,0.00002436151,0.00008750038,0.00001140735,0.00002972057,0.001849165,0.9890571,0.004157804,0.003501598,0.0008986175,0.0002150432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0819326,0.0003122465,0.8984905,0.0002958027,0.001164333,0.0002383519,0.0002029422,0.0007093786,0.01665389],"genre_scores_gemma":[0.5838595,0.00002236448,0.4136012,0.0006400747,0.0001778297,0.00001526767,0.00004617956,0.00004755122,0.001589989],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7059699,"threshold_uncertainty_score":0.9996695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01972382980271739,"score_gpt":0.2723903958376214,"score_spread":0.252666566034904,"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."}}