{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005612329,0.000618831,0.0008431429,0.0005076308,0.001039539,0.002072612,0.008449359,0.0009575728,0.000395094],"category_scores_gemma":[0.003336262,0.0005277368,0.00006448645,0.000979146,0.000329405,0.000749366,0.005568589,0.004657437,0.0001440123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002638922,"about_ca_system_score_gemma":0.0006240886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004981422,"about_ca_topic_score_gemma":0.005431077,"domain_scores_codex":[0.9947052,0.001025026,0.0009975275,0.001607161,0.0007976968,0.0008674038],"domain_scores_gemma":[0.9911297,0.0008038664,0.0008005069,0.006843989,0.0002895671,0.0001323957],"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":[0.00006192915,0.0002002159,0.0001179238,0.0004650014,0.00002428129,0.00001214058,0.0003543297,0.0007142803,0.003812922,0.001175408,0.9928449,0.0002166717],"study_design_scores_gemma":[0.0004458921,0.0000761748,0.0001698839,0.001574774,0.0001157123,0.00005930547,0.000278069,0.04054655,0.0002726551,0.000102335,0.9556494,0.000709211],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"dataset","genre_scores_codex":[0.009941076,0.1009739,0.01016729,0.03053251,0.6948547,0.01246855,0.08032545,0.005242224,0.0554943],"genre_scores_gemma":[0.2593739,0.002691409,0.09925543,0.001438896,0.005716938,0.002844014,0.4718874,0.001140115,0.1556518],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.6891378,"threshold_uncertainty_score":0.9997174,"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."}}