{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003453013,0.001662513,0.001163317,0.002528621,0.00112694,0.00222992,0.002465068,0.001094709,0.003762051],"category_scores_gemma":[0.008854148,0.0006875982,0.002112672,0.001610288,0.0008012936,0.001234489,0.001668403,0.002551975,0.002516482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001443611,"about_ca_system_score_gemma":0.003613743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005627182,"about_ca_topic_score_gemma":0.01012383,"domain_scores_codex":[0.9980484,0.0003339361,0.0002310246,0.0007510353,0.0005132122,0.0001223066],"domain_scores_gemma":[0.9963888,0.00155516,0.0003639258,0.0007302855,0.0008310705,0.0001307163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004577359,0.0006170581,0.0141625,0.0006669225,0.000384661,0.0005482385,0.0005294801,0.2136942,0.05017059,0.02390498,0.01923857,0.6756251],"study_design_scores_gemma":[0.000055668,0.00008781246,0.002071249,0.00003978234,0.00005049922,0.0001236541,0.00006387938,0.9119548,0.03743472,0.03826713,0.009778772,0.0000721022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009881505,0.00008673432,0.9663622,0.0001485406,0.00003216763,0.0002819166,0.002501175,0.01913877,0.00156681],"genre_scores_gemma":[0.06857232,0.00008172286,0.9242337,0.000116911,0.00002213676,0.0006248368,0.004268084,0.0007293166,0.001350861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005627182,"threshold_uncertainty_score":0.01826149,"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."}}