{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004684841,0.0003190873,0.0003107706,0.0002241247,0.0003857212,0.0001473995,0.001791785,0.0003044383,0.000003062188],"category_scores_gemma":[0.00006990163,0.0003783625,0.000147407,0.00002985829,0.00009823721,0.0002701113,0.001016922,0.001051895,0.00007684912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002372982,"about_ca_system_score_gemma":0.0003969652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001473396,"about_ca_topic_score_gemma":5.057938e-7,"domain_scores_codex":[0.9979339,0.0003007676,0.0002027626,0.0008211437,0.0004100117,0.0003314186],"domain_scores_gemma":[0.9980848,0.0001271933,0.0004097082,0.001019973,0.0001947658,0.0001635485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001153271,0.00001108229,0.000003792435,0.00006178255,0.00005428725,0.00007609002,0.0001730849,0.00001824112,0.0000329942,0.8700614,0.03199247,0.09750323],"study_design_scores_gemma":[0.0003080497,0.0001048818,0.00005123437,0.00009775149,0.00006459766,0.00001598514,0.00001135866,0.03308615,0.00005746265,0.00001431677,0.9657724,0.0004158498],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000008766409,0.00008517462,0.1366786,0.00001414779,0.0002655563,0.0001910844,0.00001729616,0.0005094431,0.86223],"genre_scores_gemma":[0.0001078428,0.00003549962,0.01178545,0.00003476462,0.0001515696,0.000001177773,0.0001453989,0.0000297879,0.9877085],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9337799,"threshold_uncertainty_score":0.9998668,"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."}}