{"id":"W4388567027","doi":"10.1038/s41467-023-42992-y","title":"Exploiting redundancy in large materials datasets for efficient machine learning with less data","year":2023,"lang":"en","type":"article","venue":"Nature Communications","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"Schwartz/Reisman Emergency Medicine Institute; Vector Institute; Natural Resources Canada; University of Toronto; University of New Brunswick","funders":"Office of Energy Research and Development; Natural Resources Canada; Canada First Research Excellence Fund; University of Toronto; National Institute of Standards and Technology; Alliance de recherche numérique du Canada; Western Canada Research Grid","keywords":"Computer science; Redundancy (engineering); Robustness (evolution); Machine learning; Training set; Artificial intelligence; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00662658,0.001363165,0.001644433,0.002725326,0.001045122,0.002655872,0.002701627,0.00155951,0.001931959],"category_scores_gemma":[0.02237632,0.0008348758,0.00163711,0.002885409,0.001706325,0.005270438,0.002999933,0.002628822,0.001338693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006094403,"about_ca_system_score_gemma":0.001376144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000936046,"about_ca_topic_score_gemma":0.002022808,"domain_scores_codex":[0.997057,0.001228773,0.0001827447,0.0005458689,0.0008604233,0.0001252571],"domain_scores_gemma":[0.9838832,0.00806832,0.0008801317,0.00574016,0.001194617,0.0002336095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001394454,0.00122021,0.06678545,0.002719382,0.001024324,0.001274964,0.001283007,0.2909639,0.123463,0.04087834,0.02614401,0.442849],"study_design_scores_gemma":[0.0001004803,0.0004554547,0.01747472,0.0002464682,0.0002420014,0.0006591423,0.0005296681,0.7092547,0.08117559,0.1598944,0.02980789,0.0001594662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2469265,0.002505869,0.7264703,0.003975694,0.0003583687,0.0002859186,0.007635683,0.006297739,0.005543839],"genre_scores_gemma":[0.5776499,0.000855755,0.4078779,0.0006619066,0.000243546,0.0003630123,0.01096368,0.0005245983,0.0008597486],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00662658,"threshold_uncertainty_score":0.03504509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0605409308656181,"score_gpt":0.3639573872727498,"score_spread":0.3034164564071317,"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."}}