{"id":"W2049079538","doi":"10.1016/j.jat.2015.02.007","title":"Near oracle performance and block analysis of signal space greedy methods","year":2015,"lang":"en","type":"article","venue":"Journal of Approximation Theory","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Air Force Office of Scientific Research; Azrieli Foundation; Simons Foundation","keywords":"Orthonormal basis; Compressed sensing; Block (permutation group theory); Oracle; Algorithm; Mathematics; Additive white Gaussian noise; SIGNAL (programming language); Greedy algorithm; Space (punctuation); Basis (linear algebra); Gaussian; Noise (video); Computer science; White noise; Artificial intelligence; Combinatorics; Statistics","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":[0.001167991,0.00007045813,0.000241323,0.0002344731,0.00002005795,0.00002153554,0.00007911271,0.00004174697,0.000009861471],"category_scores_gemma":[0.00004681797,0.00005903086,0.00006453253,0.0003114648,0.0000472872,0.0001773712,0.00001653193,0.0001107118,5.736198e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000021496,"about_ca_system_score_gemma":0.00001791467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001331625,"about_ca_topic_score_gemma":2.127107e-7,"domain_scores_codex":[0.9993643,0.0001039647,0.0002710363,0.00004467311,0.0001472136,0.00006878619],"domain_scores_gemma":[0.9993679,0.00008693646,0.0001912965,0.00009885331,0.0001986784,0.00005631906],"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":[0.0004630572,0.0001500213,0.003666424,0.0001639445,0.003323523,0.00001484758,0.007687178,0.7223355,0.1019324,0.01757005,0.002679399,0.1400137],"study_design_scores_gemma":[0.0002527529,0.0001406762,0.00218998,0.00005449028,0.000500354,0.00004057955,0.0003531497,0.8642694,0.1222698,0.009365932,0.0004549298,0.000107947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6717321,0.0005303482,0.3266775,0.00001769053,0.00004447371,0.0000319507,6.932876e-7,0.00003331012,0.0009319439],"genre_scores_gemma":[0.860257,0.00004820707,0.1396372,0.000008888836,0.00002671949,4.070466e-7,4.791577e-7,0.000008053165,0.00001310834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1885249,"threshold_uncertainty_score":0.2407209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02407761480701673,"score_gpt":0.2808118933087718,"score_spread":0.256734278501755,"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."}}