{"id":"W3092136498","doi":"10.1109/tpami.2021.3075372","title":"Winning Solutions and Post-Challenge Analyses of the ChaLearn AutoDL Challenge 2019","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institució Catalana de Recerca i Estudis Avançats; Centre National de la Recherche Scientifique; Chinese Academy of Sciences; CHIST-ERA; Microsoft; Agence Nationale de la Recherche; University of Edinburgh; Institut national de recherche en informatique et en automatique (INRIA); Acadia University; Google Research; Nvidia; Birla Institute of Technology and Science, Pilani; Amazon Catalyst","keywords":"Computer science; Modular design; Benchmark (surveying); Machine learning; Artificial intelligence; Variety (cybernetics); Code (set theory); Modularity (biology); Sorting; Matching (statistics); Component (thermodynamics); Deep learning; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0116874,0.003145421,0.001904249,0.002057964,0.00170752,0.003351291,0.003509382,0.002707917,0.01147522],"category_scores_gemma":[0.02779899,0.000689169,0.001557108,0.001408356,0.001677267,0.002823268,0.005320857,0.00421572,0.01194611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002581842,"about_ca_system_score_gemma":0.00216418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007909955,"about_ca_topic_score_gemma":0.01733673,"domain_scores_codex":[0.9871591,0.003879742,0.0004863185,0.001772577,0.004959593,0.001742624],"domain_scores_gemma":[0.9857296,0.004089027,0.0003258979,0.002382132,0.005811526,0.001661922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.003626535,0.002245395,0.006041036,0.001547238,0.0005183498,0.000702815,0.0006368611,0.05639772,0.007500398,0.008521619,0.686504,0.225758],"study_design_scores_gemma":[0.002347368,0.005417625,0.0250199,0.0005688893,0.0003272956,0.0009966836,0.002556741,0.5410289,0.04335638,0.02978442,0.3481129,0.0004829634],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6083761,0.008648882,0.08584581,0.01146968,0.01590109,0.001938056,0.05358853,0.05749828,0.1567337],"genre_scores_gemma":[0.6321795,0.0008636464,0.09709466,0.003725609,0.001511615,0.002238476,0.1645988,0.0113598,0.08642787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0116874,"threshold_uncertainty_score":0.0618096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0516221799101339,"score_gpt":0.3076245037159868,"score_spread":0.2560023238058529,"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."}}