{"id":"W4399353100","doi":"10.48550/arxiv.2405.20448","title":"Knockout: A simple way to handle missing inputs","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of Southern California; Biogen; BioClinica; Meso Scale Diagnostics; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Simple (philosophy); Computer science; Set (abstract data type); Epistemology; Philosophy","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002534657,0.0003879928,0.0004078421,0.0003398098,0.0002290507,0.0005319536,0.001609572,0.0002310701,0.00005966721],"category_scores_gemma":[0.00005572477,0.0004155641,0.0002867054,0.0008730152,0.00005810359,0.0002470259,0.004906256,0.0005581256,0.0005464411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002109082,"about_ca_system_score_gemma":0.0001848105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001996417,"about_ca_topic_score_gemma":0.0001000405,"domain_scores_codex":[0.997592,0.0001483672,0.0002217756,0.001443741,0.0001116729,0.0004824687],"domain_scores_gemma":[0.9981364,0.0000981442,0.0001152242,0.001180232,0.0001471386,0.0003228385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003142439,0.0001068631,0.0001273199,0.0001578399,0.0002652873,0.0008918452,0.001222285,0.9166131,0.001160416,0.03709465,0.01501722,0.02731172],"study_design_scores_gemma":[0.0002137839,0.00006730803,0.0002288185,0.0002368808,0.00009831656,0.000004606954,0.00003244842,0.8898112,0.002943053,0.08931161,0.01631602,0.0007359963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03439284,0.0001695964,0.9577919,0.001007324,0.001300153,0.0002995533,0.00002095296,0.0003194816,0.004698151],"genre_scores_gemma":[0.9880992,0.00003279959,0.007809131,0.0004364104,0.0003069135,0.000001415157,0.000008502059,0.00002893908,0.003276726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9537063,"threshold_uncertainty_score":0.9998296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0597121895342172,"score_gpt":0.1968670788490235,"score_spread":0.1371548893148063,"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."}}