{"id":"W4390579708","doi":"10.1038/s41467-023-44462-x","title":"Publisher Correction: Exploiting redundancy in large materials datasets for efficient machine learning with less data","year":2024,"lang":"en","type":"erratum","venue":"Nature Communications","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"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":"","keywords":"Redundancy (engineering); Computer science; Machine learning; Data mining; Artificial intelligence; Operating system","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":[0.005482058,0.002481022,0.002240411,0.004343234,0.004764402,0.005611231,0.003827119,0.005553492,0.0971983],"category_scores_gemma":[0.07497723,0.001443592,0.001368876,0.004016948,0.003104767,0.003887825,0.002662695,0.01161108,0.06323467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003544955,"about_ca_system_score_gemma":0.006817331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01258308,"about_ca_topic_score_gemma":0.01874845,"domain_scores_codex":[0.9934654,0.0007835125,0.0009247454,0.0008283224,0.003670497,0.0003276146],"domain_scores_gemma":[0.9445733,0.0134222,0.002140881,0.005252758,0.03292685,0.001684066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001970907,0.000004757299,0.00004404789,0.00008025362,0.000007567739,0.0001674746,0.00002925105,0.00007411792,0.0001283749,0.001555802,0.9908188,0.007069803],"study_design_scores_gemma":[0.00002414087,0.00001669262,0.0003014311,0.0001800973,0.00002536152,0.000575737,0.00005724782,0.000596649,0.001193551,0.003103798,0.9938856,0.00003971534],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"other","genre_scores_codex":[0.000374052,0.0008138716,0.005682254,0.04154333,0.937806,0.00003661833,0.003278524,0.002268741,0.008196598],"genre_scores_gemma":[0.02981832,0.009296045,0.04447294,0.07374243,0.2401008,0.0004580816,0.01558416,0.01423539,0.5722918],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.0971983,"threshold_uncertainty_score":0.3251607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04034854785299506,"score_gpt":0.3397404843589851,"score_spread":0.2993919365059901,"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."}}