{"id":"W4289099942","doi":"10.48550/arxiv.1812.09877","title":"Latent Filter Scaling for Multimodal Unsupervised Image-to-Image\\n Translation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Image translation; Artificial intelligence; Image (mathematics); Benchmark (surveying); Hyperparameter; Translation (biology); Pattern recognition (psychology); Domain (mathematical analysis); Code (set theory); Convolutional neural network; Filter (signal processing); Computer vision; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000999157,0.001063837,0.0007605728,0.0007640732,0.0004386701,0.000979104,0.001108632,0.001267636,0.005238596],"category_scores_gemma":[0.002717233,0.0003798992,0.001124132,0.0008141999,0.00110692,0.001362811,0.001561499,0.001814722,0.002483736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000960416,"about_ca_system_score_gemma":0.0007070562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00262819,"about_ca_topic_score_gemma":0.004716035,"domain_scores_codex":[0.9995021,0.0001213545,0.00002123063,0.0001676068,0.0001276462,0.00006014007],"domain_scores_gemma":[0.9992585,0.0002728546,0.00007987337,0.0002311197,0.0001066358,0.00005098847],"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":[0.0003201207,0.0002260876,0.001149768,0.0002924581,0.0001787495,0.000300404,0.0002538987,0.3868741,0.07496127,0.05419,0.01536615,0.465887],"study_design_scores_gemma":[0.00001385392,0.00004006692,0.0002655218,0.00001247272,0.00001343541,0.00009513847,0.00001988948,0.9686221,0.01354441,0.01397256,0.003385362,0.0000152533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01022017,0.0002675527,0.9852343,0.0001938684,0.00005294915,0.00004704457,0.000166724,0.001637902,0.002179411],"genre_scores_gemma":[0.3770706,0.0007297295,0.6030199,0.0006448343,0.00021145,0.0002992985,0.001666323,0.001207227,0.01515062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005238596,"threshold_uncertainty_score":0.01752484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06552722039687335,"score_gpt":0.2387616548907945,"score_spread":0.1732344344939211,"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."}}