{"id":"W4401351858","doi":"10.1088/1361-648x/ad6bdb","title":"Discovery of novel materials through machine learning","year":2024,"lang":"en","type":"review","venue":"Journal of Physics Condensed Matter","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Process (computing); Resource (disambiguation); Data science; Biochemical engineering; Chemical space; Machine learning; Artificial intelligence; Drug discovery; Engineering; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001816486,0.0007099608,0.003279348,0.0002203595,0.0000954701,0.0006600893,0.001283877,0.0002632972,0.00149258],"category_scores_gemma":[0.0001725756,0.0004799548,0.000806718,0.000385882,0.0003140036,0.0009756709,0.000499009,0.0009700115,0.0009597949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001251912,"about_ca_system_score_gemma":0.0004513733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004310408,"about_ca_topic_score_gemma":5.925875e-7,"domain_scores_codex":[0.9950338,0.0005598456,0.002405507,0.0005306765,0.0009789323,0.0004912674],"domain_scores_gemma":[0.994695,0.0003534038,0.004060674,0.000548461,0.0002637945,0.00007863531],"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":[0.00007717095,0.000354158,0.00001053585,0.05475401,0.0004162882,0.0001361535,0.0007096158,0.0004074388,0.9279755,0.002396787,0.005625213,0.007137099],"study_design_scores_gemma":[0.001610691,0.0007839128,0.00000749661,0.07357922,0.006960611,0.002408366,0.00007660934,0.0001113157,0.1402156,0.004630007,0.7670807,0.002535465],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004173583,0.9820178,0.006118232,0.0001027749,0.006114773,0.0004470398,0.00050901,0.00005643683,0.0004603269],"genre_scores_gemma":[0.002405035,0.9805241,0.01053507,0.0002438816,0.002528975,0.00002174934,0.00005902195,0.0003236692,0.003358488],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.78776,"threshold_uncertainty_score":0.9998181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04798183607334222,"score_gpt":0.3399214882782615,"score_spread":0.2919396522049192,"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."}}