{"id":"W4311710514","doi":"10.26434/chemrxiv-2022-fh0t2","title":"An Unsupervised Machine Learning Workflow for Assigning and Predicting Generality in Asymmetric Catalysis","year":2022,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Mitacs","keywords":"Generality; Workflow; Catalysis; Computer science; Identification (biology); Chemistry; Machine learning; Artificial intelligence; Organic chemistry; Database","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006085896,0.0004957737,0.0008218309,0.0005419595,0.0006185228,0.000652169,0.001212007,0.0002762228,0.0007425552],"category_scores_gemma":[0.001758007,0.0005158695,0.0001291925,0.0007375003,0.0001559968,0.0003042048,0.001619398,0.001141378,0.00000740519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002625125,"about_ca_system_score_gemma":0.0001643157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001653033,"about_ca_topic_score_gemma":0.00008271479,"domain_scores_codex":[0.9953273,0.0008178062,0.0008135188,0.001699157,0.0006058583,0.0007363604],"domain_scores_gemma":[0.9977595,0.000485311,0.0005903591,0.0008580096,0.00009431908,0.0002125303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008245301,0.0001515349,0.2736953,0.0007151964,0.00002060896,0.00001827484,0.001596584,0.2445242,0.4757169,0.00005153476,0.00002819492,0.003399141],"study_design_scores_gemma":[0.00128706,0.000206943,0.03615405,0.0002186764,0.0001306897,0.00001277576,0.0002849292,0.8876705,0.07070684,0.001261638,0.0007518686,0.001314066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911012,0.0007117467,0.005756434,0.0001814054,0.0009626108,0.0006954563,0.0000387765,0.0003305539,0.0002217923],"genre_scores_gemma":[0.952414,0.00005724888,0.04601641,0.00008460096,0.0003015997,0.0004739991,0.0004053662,0.00008185688,0.0001649561],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6431463,"threshold_uncertainty_score":0.9997293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02551712177798919,"score_gpt":0.2916732777207035,"score_spread":0.2661561559427143,"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."}}