{"id":"W3012025339","doi":"10.1016/j.matt.2020.02.012","title":"Machine-Learning-Accelerated Perovskite Crystallization","year":2020,"lang":"en","type":"article","venue":"Matter","topic":"Perovskite Materials and Applications","field":"Engineering","cited_by":145,"is_retracted":false,"has_abstract":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Perovskite (structure); Crystallization; Ternary operation; Artificial intelligence; Throughput; Materials science; Convolutional neural network; Computer science; Machine learning; Nanotechnology; Chemical engineering; Chemistry; Crystallography; 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":["insufficient_payload"],"category_scores_codex":[0.0000170462,0.00008755417,0.00008224724,0.00001548344,0.00004156285,0.00007364901,0.00007351665,0.00003359602,0.003178376],"category_scores_gemma":[0.000003122506,0.00008545686,0.00002000877,0.0001029844,0.000007843543,0.00006605522,0.00001880786,0.00007081353,0.001750057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000961665,"about_ca_system_score_gemma":0.000001965711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005254632,"about_ca_topic_score_gemma":9.057933e-7,"domain_scores_codex":[0.9996058,0.000009975662,0.0001139303,0.0001027578,0.00005335766,0.0001141413],"domain_scores_gemma":[0.9998372,0.000004782,0.00001240577,0.000073847,0.0000138472,0.00005787696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005844785,0.00001175476,0.004191121,0.000106245,0.0000206171,0.00000273905,0.0005678016,0.02656469,0.9351716,0.0002118379,0.03256254,0.0005832245],"study_design_scores_gemma":[0.0003650844,0.00002570422,0.01059988,0.00001264659,0.0000163676,0.000004215023,0.00002639669,0.1965107,0.02925913,0.00007568567,0.7627146,0.0003896191],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9195393,0.000168906,0.043584,0.004208604,0.0001708423,0.0002598345,0.00005791497,0.001391573,0.03061897],"genre_scores_gemma":[0.9979706,0.00001642175,0.000254613,0.001226518,0.0001156366,0.00002161459,0.0000961574,0.00003445365,0.0002640306],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9059125,"threshold_uncertainty_score":0.9990272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01504408682967652,"score_gpt":0.1995890263885896,"score_spread":0.1845449395589131,"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."}}