{"id":"W4225888898","doi":"10.1039/d2ob00272h","title":"A predictive and mechanistic statistical modelling workflow for improving decision making in organic synthesis and catalysis","year":2022,"lang":"en","type":"article","venue":"Organic & Biomolecular Chemistry","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":7,"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","keywords":"Workflow; Multivariate statistics; Probabilistic logic; Identification (biology); Computer science; Embedding; Process (computing); Bayesian multivariate linear regression; Statistical model; Machine learning; Biochemical engineering; Linear regression; Data mining; Artificial intelligence; Database; Engineering","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":[0.001065657,0.0002124197,0.0002931593,0.00006636227,0.0004026872,0.0001810887,0.0003320542,0.00007431253,0.001226568],"category_scores_gemma":[0.001033744,0.0002263586,0.00002753989,0.0003136422,0.00009917645,0.000084969,0.0006168304,0.0001673792,0.000003758325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001829362,"about_ca_system_score_gemma":0.000107432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003283704,"about_ca_topic_score_gemma":0.000004061114,"domain_scores_codex":[0.9979909,0.0001008406,0.0003416948,0.000789055,0.0003782142,0.0003993035],"domain_scores_gemma":[0.9990098,0.0003917378,0.0001540479,0.0003064866,0.00003979408,0.00009809726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008671029,0.00003415849,0.00005933508,0.0001500325,0.00000608073,0.00003788074,0.0001862004,0.0005050394,0.9975631,0.00003649054,0.000002978908,0.001332002],"study_design_scores_gemma":[0.0003278157,0.00006138931,0.00004406329,0.00007319246,0.00009312107,0.0001220167,0.0002966443,0.3570403,0.6393433,0.002270078,0.00001385394,0.000314251],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3551491,0.0001253462,0.6443607,0.0000318951,0.0000599401,0.0001512599,0.00006781376,0.0000412847,0.0000126549],"genre_scores_gemma":[0.9332451,0.000006954902,0.06651802,0.00003495578,0.00002874315,0.00009715315,0.00001361648,0.00004099019,0.00001448135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.578096,"threshold_uncertainty_score":0.9996864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00552659246815115,"score_gpt":0.2297892957454442,"score_spread":0.2242627032772931,"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."}}