{"id":"W4398151028","doi":"10.1039/d4ta01942c","title":"Beyond molecular structure: critically assessing machine learning for designing organic photovoltaic materials and devices","year":2024,"lang":"en","type":"article","venue":"Journal of Materials Chemistry A","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Division of Materials Research; Office of Naval Research; Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Air Force Office of Scientific Research; Defense Advanced Research Projects Agency; Vector Institute; National Science Foundation","keywords":"Photovoltaic system; Computer science; Field (mathematics); Selection (genetic algorithm); Nanotechnology; Systems engineering; Artificial intelligence; Materials science; Engineering; Electrical 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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003237483,0.0004057965,0.0007694904,0.0001112904,0.0002843094,0.002848355,0.0005526538,0.0002100299,0.004071694],"category_scores_gemma":[0.001818764,0.0003350165,0.00008698741,0.0001769733,0.0002103522,0.0008422313,0.0002030865,0.000280131,0.00001354273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000941022,"about_ca_system_score_gemma":0.0002491338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001455409,"about_ca_topic_score_gemma":7.410492e-7,"domain_scores_codex":[0.9968155,0.0003360176,0.001189308,0.0005382278,0.000556016,0.0005649128],"domain_scores_gemma":[0.9980662,0.0004801469,0.0006377976,0.0002272291,0.0003762754,0.0002122862],"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":[0.00009896698,0.00001840744,0.00004017104,0.001735217,0.0000315426,0.0001522119,0.0001516746,0.0001978515,0.9973783,0.00005548755,0.0000568576,0.00008324994],"study_design_scores_gemma":[0.0004006556,0.0001167507,0.00007801079,0.0006180319,0.0001406026,0.001290523,0.00008310194,0.0003931836,0.9939441,0.00208244,0.0004924846,0.0003601115],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862871,0.001162635,0.01021762,0.0002701006,0.001603273,0.0001980582,0.00009696237,0.0001161786,0.00004802037],"genre_scores_gemma":[0.9614479,0.00003175787,0.03746562,0.0001527956,0.0007151779,0.00001036478,0.00002160653,0.00008309282,0.0000716691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.027248,"threshold_uncertainty_score":0.9999102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008644657789486934,"score_gpt":0.2742310247993633,"score_spread":0.2655863670098764,"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."}}