{"id":"W4367840460","doi":"10.1016/j.matt.2023.03.028","title":"Machine learning for materials science: Barriers to broader adoption","year":2023,"lang":"en","type":"article","venue":"Matter","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Sandia National Laboratories; U.S. Department of Energy","keywords":"Data science; Engineering ethics; Computer science; Nanotechnology; Engineering; Materials science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.003552502,0.0002239131,0.0002705209,0.0004145704,0.0008848615,0.0007285583,0.0008044707,0.00006692627,0.01437974],"category_scores_gemma":[0.001067666,0.0001965231,0.00004637027,0.0009025341,0.0002780104,0.0004490883,0.0003951496,0.000098278,0.01609439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008681085,"about_ca_system_score_gemma":0.0001154002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009858252,"about_ca_topic_score_gemma":0.000003068255,"domain_scores_codex":[0.9972174,0.000135027,0.000382022,0.0007520149,0.0006142965,0.0008992741],"domain_scores_gemma":[0.9988464,0.0001008593,0.0001314761,0.0004108735,0.0001389878,0.0003714348],"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":[0.00003971838,0.000004944879,0.002884872,0.00004775156,0.000001245195,0.000002183305,0.000531399,0.005363078,0.9832152,0.0002129632,0.007570102,0.0001265566],"study_design_scores_gemma":[0.0005183488,0.0001966912,0.02251862,0.00006801356,0.00001610411,0.00001302772,0.0002407546,0.005768523,0.928445,0.001030187,0.04053674,0.0006479598],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894315,0.000005938534,0.00272984,0.003395874,0.002302358,0.0005793988,0.00005611874,0.0005340606,0.000964915],"genre_scores_gemma":[0.9833551,0.000001880605,0.007455441,0.003133386,0.0003001869,0.000229782,0.00003078831,0.00005619037,0.005437263],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05477015,"threshold_uncertainty_score":0.9865212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01416478718805993,"score_gpt":0.288552353414471,"score_spread":0.2743875662264111,"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."}}