{"id":"W4365816438","doi":"10.1002/adts.202300081","title":"Unconstrained Machine Learning Screening for New Li‐Ion Cathode Materials Enhanced by Class Balancing","year":2023,"lang":"en","type":"article","venue":"Advanced Theory and Simulations","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Government of Ontario","keywords":"Battery (electricity); Cathode; Voltage; Computer science; Lithium (medication); Class (philosophy); Stability (learning theory); Power (physics); Materials science; Algorithm; Machine learning; Artificial intelligence; Chemistry; Physics; Thermodynamics; Engineering; Electrical engineering; Physical chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.002052779,0.0002394051,0.0003474493,0.0001425771,0.0008525143,0.0002037201,0.0002350598,0.00009061931,0.0007056743],"category_scores_gemma":[0.002124307,0.000226975,0.00004042678,0.0003404666,0.0001421327,0.0004741225,0.0001196981,0.0001277561,0.00005183327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002749546,"about_ca_system_score_gemma":0.00004561508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003097212,"about_ca_topic_score_gemma":0.00001484718,"domain_scores_codex":[0.9978532,0.0004588577,0.0004301773,0.0005462448,0.0002060949,0.0005054222],"domain_scores_gemma":[0.9971479,0.002150396,0.0002365553,0.0002513741,0.00007080476,0.0001429507],"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":[0.0001333503,0.000006662081,0.00006684389,0.00002065327,0.000005217835,5.390301e-7,0.0004785992,0.2518821,0.7376615,0.00664839,0.0000315494,0.003064496],"study_design_scores_gemma":[0.001666946,0.0001933984,0.0004110528,0.000139713,0.00005751212,0.000004312661,0.0003631377,0.1452975,0.8184853,0.02789215,0.004904791,0.0005842037],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7180999,0.00005275481,0.2800413,0.0001876516,0.0004692963,0.0003578611,0.000250239,0.0004312445,0.0001097823],"genre_scores_gemma":[0.9778361,0.00001737464,0.01924621,0.0001521967,0.0001304553,0.00004124028,0.000399008,0.00004178485,0.002135644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2607951,"threshold_uncertainty_score":0.9255773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01350140805368501,"score_gpt":0.2952764360415423,"score_spread":0.2817750279878573,"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."}}