{"id":"W4392704564","doi":"10.29363/nanoge.matsus.2024.151","title":"Prediction Robustness and Data Redundancy in Machine Learning for Materials Science","year":2023,"lang":"en","type":"article","venue":"","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; University of Toronto","funders":"","keywords":"Robustness (evolution); Computer science; Redundancy (engineering); Machine learning; Artificial intelligence; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.03006556,0.00148425,0.002919555,0.002260008,0.001302526,0.004713291,0.002430532,0.002758693,0.001396774],"category_scores_gemma":[0.1008699,0.001204496,0.001720994,0.002333915,0.004397908,0.007073467,0.005314289,0.006501669,0.0008540404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002457874,"about_ca_system_score_gemma":0.002035922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002308793,"about_ca_topic_score_gemma":0.001174997,"domain_scores_codex":[0.9790317,0.01257103,0.001334534,0.002277217,0.004210427,0.0005750741],"domain_scores_gemma":[0.8628879,0.1132973,0.003980548,0.01374209,0.005290657,0.000801518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009838449,0.0002448829,0.01099275,0.001124862,0.0007141968,0.0003758192,0.0006064469,0.5125537,0.004300513,0.1832812,0.01331018,0.2715116],"study_design_scores_gemma":[0.00002535246,0.0001206413,0.00111487,0.0001407889,0.00004791638,0.00007371717,0.00006164924,0.7851691,0.003283806,0.2066014,0.003312294,0.00004856037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06269757,0.0204119,0.8872446,0.02043585,0.0009313729,0.0001591568,0.000775723,0.001842729,0.005501093],"genre_scores_gemma":[0.7621523,0.008296586,0.2189519,0.002654707,0.002845506,0.000462279,0.001696204,0.0004546457,0.002485923],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03006556,"threshold_uncertainty_score":0.1590038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05732945414698173,"score_gpt":0.2881150647884438,"score_spread":0.2307856106414621,"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."}}