{"id":"W4390948539","doi":"10.1039/d3dd00199g","title":"Reproducibility in materials informatics: lessons from ‘A general-purpose machine learning framework for predicting properties of inorganic materials’","year":2024,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Advanced Scientific Computing Research; U.S. Department of Energy","keywords":"Informatics; Materials informatics; Computer science; Health informatics; Data science; Engineering; Engineering informatics; Medicine","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"],"consensus_categories":[],"category_scores_codex":[0.002928173,0.0003632092,0.00069394,0.0001861542,0.0001360106,0.002550313,0.0006537057,0.0001663361,0.0003443843],"category_scores_gemma":[0.005383962,0.0002909177,0.00009490567,0.0003290614,0.000258774,0.003287201,0.0005568132,0.0002268689,0.00009940445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001138512,"about_ca_system_score_gemma":0.0001807781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007638441,"about_ca_topic_score_gemma":0.00002157045,"domain_scores_codex":[0.9961821,0.0002106464,0.001432095,0.001148999,0.0004642475,0.0005618442],"domain_scores_gemma":[0.997963,0.0003634194,0.0004064019,0.001113948,0.00007952307,0.00007367714],"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":[0.0001799228,0.00007192941,0.0035219,0.0009448114,0.00001423477,0.000004708053,0.002369171,0.001095154,0.9888434,0.002518712,0.00001669785,0.0004193123],"study_design_scores_gemma":[0.0002165468,0.0001242774,0.002503102,0.001235218,0.00002248533,0.000007516639,0.0003418599,0.002060982,0.9843976,0.00852715,0.0001947324,0.0003685096],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889047,0.0004539035,0.005074131,0.0001807561,0.002084723,0.0007126188,0.002197105,0.0002911795,0.0001009046],"genre_scores_gemma":[0.993952,0.00002680911,0.004913674,0.00004556242,0.0003716313,0.0001120035,0.0002463199,0.00006456946,0.0002674504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006008438,"threshold_uncertainty_score":0.9999543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02382068067150253,"score_gpt":0.2753458697987379,"score_spread":0.2515251891272353,"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."}}