{"id":"W3199268650","doi":"10.23977/jaip.2020.040104","title":"Progressive Sampling-Based Joint Automatic Model Selection of Machine Learning and Feature Selection","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Feature selection; Hyperparameter; Model selection; Selection (genetic algorithm); Data pre-processing; Bayesian optimization; Preprocessor; Feature (linguistics); Bayesian inference; Bayesian probability","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001436432,0.0001266523,0.0002368869,0.0002094003,0.0002001147,0.0002431885,0.0001894986,0.00008960097,0.00002330081],"category_scores_gemma":[0.004714246,0.0001143722,0.00007466988,0.0006807442,0.00004297605,0.001125669,0.00005957607,0.0007956004,0.000004066223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006370462,"about_ca_system_score_gemma":0.0004060511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001720994,"about_ca_topic_score_gemma":0.00001246263,"domain_scores_codex":[0.9981367,0.0004272038,0.0006038235,0.0002381858,0.0004352918,0.0001588179],"domain_scores_gemma":[0.9965323,0.0005382881,0.001417959,0.000135769,0.001287798,0.00008789055],"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":[0.0002280954,0.0007664388,0.001157846,0.0001787294,0.0001261083,0.00005066239,0.001763763,0.2631367,0.09523108,0.01889152,0.0001047817,0.6183643],"study_design_scores_gemma":[0.00004583364,0.0003054637,0.0001699155,0.00009082301,0.00005516562,0.0006095783,0.0002364637,0.9334576,0.06236923,0.001797767,0.0007611269,0.0001010356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01353416,0.0005102066,0.9803519,0.005227371,0.0001512862,0.00007526399,0.000001026924,0.00004326353,0.0001055227],"genre_scores_gemma":[0.6382697,0.00006930023,0.3614495,0.00008797356,0.00007429806,0.000001887648,0.000003122575,0.000007871241,0.00003631223],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6703209,"threshold_uncertainty_score":0.5643734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05521239643834797,"score_gpt":0.3527493733478377,"score_spread":0.2975369769094898,"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."}}