{"id":"W4407632278","doi":"10.48550/arxiv.2502.09794","title":"Reconstruction of frequency-localized functions from pointwise samples via least squares and deep learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Austrian Science Fund","keywords":"Pointwise; Least-squares function approximation; Deep learning; Mathematics; Artificial intelligence; Computer science; Statistics; Mathematical analysis","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":[0.0004844259,0.0002912445,0.0005152547,0.0002761074,0.0002339452,0.0001414546,0.0005742182,0.0002783444,0.00007330038],"category_scores_gemma":[0.0003742088,0.000295527,0.000174744,0.0002912105,0.0001763239,0.0002964719,0.000805372,0.0007580145,0.00001786307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005539892,"about_ca_system_score_gemma":0.0001513262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00220785,"about_ca_topic_score_gemma":0.00008910026,"domain_scores_codex":[0.9976617,0.000551502,0.0005258062,0.0007926316,0.0002179478,0.0002503809],"domain_scores_gemma":[0.9981177,0.0004864277,0.0003472441,0.0007278686,0.0002320263,0.00008868119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007354394,0.00008068053,0.3287834,0.000269437,0.0003090905,0.00002363445,0.001845534,0.001478986,0.0291202,0.0008911469,0.00006804211,0.6370563],"study_design_scores_gemma":[0.003575412,0.0004091594,0.6961326,0.002808433,0.0006793151,0.0001428067,0.0008469134,0.09613176,0.03000844,0.1640433,0.00294525,0.002276578],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3101868,0.001709406,0.6858764,0.0001530867,0.00111622,0.0001324375,0.00001716863,0.000143503,0.0006650211],"genre_scores_gemma":[0.6984295,0.0003261158,0.3000888,0.0001231057,0.0002258524,0.00003216732,0.00005851073,0.00002021412,0.0006957837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6347798,"threshold_uncertainty_score":0.9999497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03769163261781937,"score_gpt":0.2743325790042647,"score_spread":0.2366409463864453,"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."}}