{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003136711,0.0001083577,0.0001056601,0.0001547765,0.0001571323,0.0009511455,0.0003051953,0.00005939942,0.000001417977],"category_scores_gemma":[0.00007020209,0.00007230877,0.00001237094,0.0002188136,0.00003136964,0.0100727,0.0001171424,0.00006089985,0.00001873847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004768126,"about_ca_system_score_gemma":0.00003820531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001987631,"about_ca_topic_score_gemma":2.034754e-7,"domain_scores_codex":[0.9990273,0.00003317079,0.0003806147,0.0001580039,0.0002300726,0.0001709061],"domain_scores_gemma":[0.9992539,0.00002934181,0.0002406087,0.0002653965,0.0001517195,0.00005904826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005742025,0.000007963952,0.001019257,0.0002921654,0.000004688232,0.000001296144,0.002145202,0.0000320649,0.002826302,0.00373462,0.006554934,0.9833758],"study_design_scores_gemma":[0.001022374,0.0003217805,0.004642302,0.002364248,0.00001141328,0.0007793456,0.0002444242,0.896428,0.01084853,0.0006000127,0.08209531,0.0006422832],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07409646,0.0002012369,0.9182176,0.001171393,0.0008275343,0.0003652888,0.00004043968,0.001888598,0.003191459],"genre_scores_gemma":[0.9944967,0.000009859365,0.005083153,0.0001014621,0.00007057571,0.00003732686,0.00001068699,0.000004704928,0.0001855046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9827335,"threshold_uncertainty_score":0.9171917,"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."}}