{"id":"W2972197134","doi":"10.1002/adma.201907801","title":"Beyond Ternary OPV: High‐Throughput Experimentation and Self‐Driving Laboratories Optimize Multicomponent Systems","year":2020,"lang":"en","type":"preprint","venue":"Advanced Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS); Bayerisches Staatsministerium für Umwelt und Verbraucherschutz; Tata Sons; Bayerisches Staatsministerium für Wirtschaft und Medien, Energie und Technologie; Natural Resources Canada; Deutsche Forschungsgemeinschaft","keywords":"Ternary operation; Component (thermodynamics); Bayesian optimization; Throughput; Stability (learning theory); Computer science; Materials science; Nanotechnology; Artificial intelligence; Machine learning; Physics; Operating system","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001325667,0.0008809169,0.001422876,0.0001294917,0.0003936578,0.001870998,0.001003712,0.0003667203,0.0004439433],"category_scores_gemma":[0.000459308,0.0008446182,0.00006389058,0.0001510493,0.0002870368,0.000858912,0.002503067,0.0003190872,0.0002020724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003233324,"about_ca_system_score_gemma":0.0002041609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006461607,"about_ca_topic_score_gemma":0.000004079393,"domain_scores_codex":[0.9941784,0.0008400528,0.001348899,0.001869219,0.001011101,0.0007523652],"domain_scores_gemma":[0.9968498,0.0002332635,0.001298981,0.0009988872,0.0003166707,0.0003023994],"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":[0.00011148,0.00007950768,0.00005725325,0.0007185994,0.00002877085,0.00005019018,0.001492096,0.02635611,0.9690565,0.001845248,0.0001714399,0.00003282097],"study_design_scores_gemma":[0.0009982283,0.000167943,0.0008149135,0.000472762,0.0000899661,0.0000309622,0.000382256,0.002418734,0.9902376,0.002274917,0.000988888,0.00112284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9743136,0.001038688,0.005078556,0.0004647188,0.0157603,0.001565771,0.0005786708,0.00105389,0.0001457983],"genre_scores_gemma":[0.8131227,0.0003553344,0.1846091,0.0001744889,0.0008507075,0.0005303051,0.0001795173,0.0001276977,0.00005017674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1795305,"threshold_uncertainty_score":0.9994004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0113259337031943,"score_gpt":0.2823632016110761,"score_spread":0.2710372679078818,"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."}}