{"id":"W4415329183","doi":"10.48550/arxiv.2505.15661","title":"Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Artificial neural network; Permutation (music); Greedy algorithm; Differentiable function; Matching (statistics); Matching pursuit; Sorting; Sparse matrix","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001561227,0.001073887,0.0008978265,0.0005568659,0.0005024789,0.000913297,0.001390308,0.001261077,0.003555005],"category_scores_gemma":[0.006825448,0.000565432,0.0005243639,0.0007540233,0.001460691,0.001877243,0.002238249,0.002185471,0.001213546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007013492,"about_ca_system_score_gemma":0.001481669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002199377,"about_ca_topic_score_gemma":0.003448666,"domain_scores_codex":[0.9992797,0.0002576727,0.00003365957,0.000124035,0.0002233958,0.00008151038],"domain_scores_gemma":[0.9984576,0.0008628268,0.0001151699,0.0003145969,0.000174396,0.00007545878],"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":[0.0002825879,0.0001283216,0.0008663344,0.0001265432,0.00005789647,0.0001273618,0.000190239,0.6133192,0.01047989,0.09190888,0.00468939,0.2778234],"study_design_scores_gemma":[0.00001220323,0.00003091847,0.000040472,0.000006645217,0.000002879909,0.00001888254,0.000009716042,0.9730105,0.002053394,0.02403791,0.0007711649,0.000005290653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004086573,0.00004611065,0.9946567,0.00008313012,0.00001586557,0.00001827275,0.00001603395,0.0004390805,0.0006383148],"genre_scores_gemma":[0.1922868,0.0001815005,0.8035656,0.0002407878,0.00006904387,0.0001709385,0.0001822795,0.000421098,0.002881853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003555005,"threshold_uncertainty_score":0.01189268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09070965776957313,"score_gpt":0.3029128019324848,"score_spread":0.2122031441629117,"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."}}