{"id":"W4200001896","doi":"10.3233/faia210316","title":"Data-Centric Machine Learning: Improving Model Performance and Understanding Through Dataset Analysis","year":2021,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Classifier (UML); Training set; Metric (unit); Performance metric; Test set; Test data; Process (computing); Set (abstract data type); Data set; Data mining; Domain (mathematical analysis); Labeled data; Engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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"],"consensus_categories":[],"category_scores_codex":[0.0004147752,0.0002601593,0.000377399,0.000396419,0.000403699,0.0003518333,0.000870464,0.0001694042,0.00001321591],"category_scores_gemma":[0.00003217874,0.0002764025,0.00004025165,0.0004921212,0.0001598953,0.00061733,0.0007203974,0.0006156583,0.000009056917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009159688,"about_ca_system_score_gemma":0.00008724797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005303395,"about_ca_topic_score_gemma":0.000128436,"domain_scores_codex":[0.997891,0.00003526374,0.0004996599,0.001100687,0.0002318094,0.0002415746],"domain_scores_gemma":[0.9982591,0.0000792693,0.0002839549,0.001249383,0.00004111745,0.00008719785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006262393,0.00003670876,0.0006406137,0.00007203595,0.0001165258,0.000002959106,0.0001913559,0.009220057,0.000005922395,0.6945727,0.0008505561,0.2942843],"study_design_scores_gemma":[0.00001858443,0.00001139709,0.0000124539,0.00002392691,0.0001626093,0.00000390616,0.0001242212,0.913389,0.000009521743,0.03958716,0.04638714,0.000270106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000007261177,0.002130337,0.9918193,0.00036532,0.00006400014,0.0002524691,0.0008549599,0.00005968502,0.004446658],"genre_scores_gemma":[0.2008857,0.06823183,0.5899311,0.0006953126,0.0006327633,0.0003045143,0.09885614,0.0001884874,0.0402742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9041689,"threshold_uncertainty_score":0.9999688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1220128723694561,"score_gpt":0.3056667902057088,"score_spread":0.1836539178362527,"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."}}