{"id":"W4318148225","doi":"10.1109/bigdata55660.2022.10020386","title":"Adaptive Method for Machine Learning Model Selection in Data Science Projects","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Selection (genetic algorithm); Machine learning; Process (computing); Heuristics; Feature selection; Model selection; Artificial intelligence; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005531415,0.00023625,0.0002271603,0.0009363489,0.0004663224,0.0005056286,0.02152296,0.00004454443,0.00004310672],"category_scores_gemma":[0.003437208,0.0002587308,0.00002022214,0.001512878,0.00009423188,0.003106384,0.0162759,0.001017962,0.00001570304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004532275,"about_ca_system_score_gemma":0.001708324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005706761,"about_ca_topic_score_gemma":0.0005372976,"domain_scores_codex":[0.9946086,0.0002236878,0.0003755367,0.002258941,0.001987331,0.0005459514],"domain_scores_gemma":[0.9952162,0.0008247124,0.0001763452,0.00335621,0.000303188,0.0001233606],"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":[0.0005551873,0.0008490575,0.00192063,0.00006556102,0.0001888419,0.00007926275,0.0008684627,0.1977151,0.01901194,0.05619213,0.02628268,0.6962711],"study_design_scores_gemma":[0.0005226916,0.000149414,0.0002182224,0.00002679622,0.000005490677,0.000028235,0.00006513614,0.9884093,0.0003301831,0.0007008202,0.009274444,0.0002692922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008434698,0.00003000243,0.9849275,0.001071936,0.00197954,0.0005302154,0.01016896,0.0001747133,0.0002736131],"genre_scores_gemma":[0.7386898,0.00009132178,0.2425025,0.0002646273,0.0004967786,0.0003035716,0.01685787,0.00004804716,0.0007454802],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7906941,"threshold_uncertainty_score":0.9999865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4726800557815008,"score_gpt":0.4217361885031067,"score_spread":0.05094386727839412,"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."}}