{"id":"W4256280104","doi":"10.26434/chemrxiv.12824522","title":"Optimization of the Bulk Heterojunction of All-smallmolecule Organic Photovoltaics Using Design of Experiment and Machine Learning Approaches","year":2020,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Organic Electronics and Photovoltaics","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Technische Universität München; Mitacs; Canada Research Chairs; University of Alberta; Alberta Innovates - Technology Futures","keywords":"Organic solar cell; Simulated annealing; Materials science; Photovoltaic system; Acceptor; Polymer solar cell; Parameter space; Computer science; Annealing (glass); Design of experiments; Artificial intelligence; Machine learning; Optoelectronics; Energy conversion efficiency; Mathematics; Physics; Electrical engineering; Engineering; Statistics","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":[0.001375527,0.0007762519,0.0008409262,0.0004060562,0.0002381913,0.0009902512,0.0003721375,0.0004584704,0.0006508901],"category_scores_gemma":[0.001212867,0.0004358119,0.0005731278,0.0003318751,0.0004284745,0.0004769185,0.0003100043,0.0006555495,0.00009922934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007067352,"about_ca_system_score_gemma":0.0007613018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005692697,"about_ca_topic_score_gemma":0.001409084,"domain_scores_codex":[0.9996557,0.0001088674,0.00001586353,0.00007515818,0.0001128833,0.00003158506],"domain_scores_gemma":[0.9995297,0.0003305298,0.00005052179,0.00003308746,0.00004764523,0.000008529765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001316709,0.0001551505,0.001023617,0.000299624,0.0001089617,0.00006787656,0.00002960648,0.8949606,0.07210336,0.004079179,0.0001520707,0.02688835],"study_design_scores_gemma":[0.00003008963,0.0004689272,0.000764746,0.00001630049,0.00004774669,0.00001649441,0.00002732459,0.9508162,0.04411915,0.00264772,0.001031296,0.00001412048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5952036,0.001736428,0.3932203,0.0002107449,0.00004812283,0.0003089168,0.0003809966,0.0003082482,0.008582542],"genre_scores_gemma":[0.871782,0.0006788851,0.1257328,0.00005520769,0.000009027649,0.0003706796,0.0001771957,0.00005275465,0.001141469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001375527,"threshold_uncertainty_score":0.007274568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05731789899916363,"score_gpt":0.2171763146830616,"score_spread":0.159858415683898,"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."}}