{"id":"W4324148852","doi":"10.26434/chemrxiv-2022-fh0t2-v2","title":"An Unsupervised Machine Learning Workflow for Assigning and Predicting Generality in Asymmetric Catalysis","year":2023,"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; Computer science; Catalysis; Identification (biology); Machine learning; Chemistry; 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":[0.005962869,0.0005089344,0.000846423,0.0006088169,0.0003964443,0.0007699081,0.001049767,0.0004062951,0.0001022033],"category_scores_gemma":[0.002721918,0.0005082966,0.0001249219,0.0008212866,0.0001743215,0.0003032463,0.001111765,0.0008752986,0.00003290814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001656263,"about_ca_system_score_gemma":0.0001361152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002026072,"about_ca_topic_score_gemma":0.0001950916,"domain_scores_codex":[0.9955742,0.0005464867,0.0008416939,0.001722784,0.0005199428,0.0007949205],"domain_scores_gemma":[0.9976618,0.0006152975,0.0005321536,0.0008307911,0.0001301193,0.0002298372],"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":[0.00005919452,0.00009467741,0.265143,0.0009598411,0.00002295558,0.00002015126,0.001291219,0.1672714,0.5621103,0.00003775225,0.00004566511,0.002943784],"study_design_scores_gemma":[0.0008807704,0.0001056037,0.04914079,0.0004280112,0.00009645422,0.000006345984,0.0001252203,0.858998,0.0873805,0.001747286,0.0001286273,0.0009624002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9860378,0.0003565625,0.01083737,0.0002688354,0.001104076,0.0006621768,0.00003193591,0.0006268914,0.00007436924],"genre_scores_gemma":[0.9529643,0.00007102459,0.04548389,0.00005445036,0.0004249794,0.0003178514,0.0003319485,0.0001088132,0.0002427349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6917266,"threshold_uncertainty_score":0.9997368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04030047522185252,"score_gpt":0.3027772063117274,"score_spread":0.2624767310898749,"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."}}