{"id":"W2551857043","doi":"","title":"Launch and Iterate: Reducing Prediction Churn","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Machine learning; Classifier (UML); Benchmark (surveying); Artificial intelligence; Usability; Operator (biology); Markov chain; Monte Carlo method; Mathematical optimization; Mathematics; Statistics","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":[0.006843185,0.001152659,0.001882011,0.0009698988,0.0008822578,0.001354884,0.002978078,0.002459132,0.001606128],"category_scores_gemma":[0.0374422,0.0009787389,0.001070208,0.0007156654,0.002110028,0.003328057,0.003508403,0.00353776,0.0008733585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001051131,"about_ca_system_score_gemma":0.002652299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00328941,"about_ca_topic_score_gemma":0.00340275,"domain_scores_codex":[0.9962744,0.001410557,0.0001851449,0.0006884687,0.001148278,0.000293307],"domain_scores_gemma":[0.9760873,0.01555877,0.001816927,0.003755581,0.002145959,0.0006354892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007050936,0.0004414196,0.007378304,0.0001193676,0.0001163358,0.0002398419,0.000796414,0.7228616,0.01366653,0.01806774,0.004461861,0.2311454],"study_design_scores_gemma":[0.00001205813,0.000057715,0.0001472946,0.000005086207,0.000006018195,0.00001790815,0.00001413674,0.9944471,0.001436014,0.003639071,0.0002108061,0.000006714696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06365862,0.0002173807,0.9318861,0.0005010628,0.00004721496,0.0001136678,0.0000398306,0.002678378,0.0008575898],"genre_scores_gemma":[0.6907898,0.0001395077,0.3052122,0.000399584,0.0001130173,0.0002605238,0.000215448,0.0006256437,0.002244431],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006843185,"threshold_uncertainty_score":0.03619063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01383656552888091,"score_gpt":0.2326989134256209,"score_spread":0.21886234789674,"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."}}