{"id":"W2740333758","doi":"10.24963/ijcai.2017/352","title":"Learning Feature Engineering for Classification","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature engineering; Feature (linguistics); Computer science; Feature selection; Artificial intelligence; Feature vector; Machine learning; Transformation (genetics); Aggregate (composite); Set (abstract data type); Artificial neural network; Process (computing); Data mining; Pattern recognition (psychology); Deep learning","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":[0.0002400364,0.00006130656,0.00005702361,0.00003688507,0.0004599989,0.0005168868,0.000729124,0.00004462316,0.000003149786],"category_scores_gemma":[0.0005196166,0.00005447027,0.00002973063,0.00002933002,0.000008939945,0.0005141649,0.00008482633,0.0001245245,0.00002875132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001306865,"about_ca_system_score_gemma":0.00001367228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001080798,"about_ca_topic_score_gemma":0.000002368397,"domain_scores_codex":[0.9995016,0.00001048667,0.00006527717,0.0002218783,0.00007987792,0.0001208323],"domain_scores_gemma":[0.9990798,0.00005586382,0.00009917479,0.0006806543,0.00004631601,0.00003821532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003666841,0.00001667678,0.006691854,0.0000268855,0.000009090489,4.91289e-7,0.0001528207,0.0004112232,0.01260167,0.6697097,0.004622946,0.305753],"study_design_scores_gemma":[0.0001139309,0.00002310459,0.08381814,0.000005083786,0.0000015716,0.000001528495,0.000007550541,0.755563,0.0002882028,0.0001826809,0.159921,0.00007422988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009845926,0.00001178769,0.9837308,0.007907567,0.0001941767,0.00008834281,5.891434e-7,0.0002679453,0.006814227],"genre_scores_gemma":[0.8461817,0.000005801857,0.1477183,0.00004613659,0.0001018057,0.0000275538,0.00001917104,0.000006506319,0.005893097],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8451971,"threshold_uncertainty_score":0.4984351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02701836804495996,"score_gpt":0.2871792180817002,"score_spread":0.2601608500367402,"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."}}