{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003136294,0.0001885233,0.0003061849,0.0003091856,0.0003859957,0.0001034955,0.0004044719,0.00007146478,0.00008708351],"category_scores_gemma":[0.00002373499,0.0001429742,0.0002321193,0.001031078,0.0001114157,0.0002207166,0.00002897135,0.0003570543,0.000008412247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001687765,"about_ca_system_score_gemma":0.00004338155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00143654,"about_ca_topic_score_gemma":0.001604529,"domain_scores_codex":[0.9983281,0.0002502055,0.0003742001,0.0005501013,0.0002851504,0.0002122184],"domain_scores_gemma":[0.9985687,0.0001914084,0.0001739521,0.0008122793,0.0001607389,0.00009288873],"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":[0.000006513032,0.000277259,0.0009444014,0.00004941813,0.0007374004,0.000006890977,0.0012955,0.01165436,0.004028745,0.001688281,0.000009786698,0.9793015],"study_design_scores_gemma":[0.0003212401,0.0003709068,0.04696219,0.0001565173,0.001871616,0.00006661371,0.0006662585,0.849168,0.09800527,0.0009075881,0.0007263687,0.0007774362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004601324,0.001675681,0.9872939,0.005949814,0.0001220558,0.00006887716,0.00005686076,0.00005097308,0.0001805441],"genre_scores_gemma":[0.9960251,0.002590846,0.0008174257,0.0001996253,0.00001426937,0.000008459581,0.00001210537,0.000008430035,0.0003237748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9914237,"threshold_uncertainty_score":0.5830318,"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."}}