{"id":"W7117079245","doi":"","title":"SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Benchmark (surveying); Deconvolution; Sample (material); Process (computing); Lossy compression; Distribution (mathematics); Gaussian; Bridge (graph theory)","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":[0.001185393,0.0005618204,0.0005449851,0.0005981769,0.001115909,0.0003636233,0.001748122,0.0002787505,0.00001826185],"category_scores_gemma":[0.0003271,0.0006465291,0.0002509655,0.002466573,0.0003245782,0.002040465,0.0006458456,0.0005685239,0.00001934923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001080255,"about_ca_system_score_gemma":0.0009485895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004131153,"about_ca_topic_score_gemma":0.0004755229,"domain_scores_codex":[0.9961489,0.0004415457,0.00045918,0.001754947,0.0003752696,0.0008201749],"domain_scores_gemma":[0.9962599,0.0003685793,0.0004779221,0.001416033,0.001238807,0.0002387107],"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":[0.0005460622,0.0001407835,0.001593413,0.0001151355,0.0001888183,0.00004342995,0.0003836277,0.6458805,0.00003890944,0.3459482,0.0004144702,0.004706731],"study_design_scores_gemma":[0.002954619,0.0004042776,0.003147646,0.0004404375,0.0003475153,0.0000029488,0.0002701768,0.9635018,0.0001309429,0.02681951,0.001324113,0.0006560868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03527092,0.000131464,0.9598001,0.0007651041,0.0007768838,0.001089426,0.00001661898,0.0002605245,0.001889023],"genre_scores_gemma":[0.9870743,0.00008889906,0.01085421,0.0002977422,0.0001415631,0.000003656196,0.00001621791,0.00004073284,0.001482745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9518033,"threshold_uncertainty_score":0.9995986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1562647322113571,"score_gpt":0.2190490939221826,"score_spread":0.06278436171082552,"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."}}