{"id":"W4245055982","doi":"10.1017/cbo9780511921803","title":"Evaluating Learning Algorithms","year":2011,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":753,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Resampling; Interdependence; Field (mathematics); Process (computing); Classifier (UML); Algorithm; Management science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01587596,0.001892937,0.001758145,0.002992241,0.0007804467,0.007575775,0.002308666,0.002569759,0.01758493],"category_scores_gemma":[0.08062258,0.0003756514,0.0008944256,0.002667618,0.001598647,0.005764205,0.002193948,0.001846805,0.008212416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002123566,"about_ca_system_score_gemma":0.001652628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006026435,"about_ca_topic_score_gemma":0.0007153722,"domain_scores_codex":[0.970924,0.01184547,0.001464337,0.002001899,0.01329857,0.0004657268],"domain_scores_gemma":[0.959121,0.0292467,0.00124702,0.003490392,0.006388702,0.0005061199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002081909,0.0001117295,0.001713662,0.001189584,0.0001808502,0.00006863488,0.0002046612,0.03990015,0.00154532,0.1320376,0.04448029,0.7783593],"study_design_scores_gemma":[0.0001654658,0.001042941,0.003216753,0.002799228,0.0003205527,0.0008626026,0.0007128069,0.2703566,0.01603126,0.3452406,0.3591016,0.0001497141],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01797654,0.03165271,0.748911,0.004192261,0.003019235,0.0007701178,0.001315385,0.002806231,0.1893566],"genre_scores_gemma":[0.1730005,0.02180362,0.7438771,0.001520088,0.001637775,0.001235932,0.003992847,0.001896223,0.0510359],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01758493,"threshold_uncertainty_score":0.08396113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06511601777908724,"score_gpt":0.2686649979806887,"score_spread":0.2035489802016015,"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."}}