{"id":"W4389821359","doi":"10.48550/arxiv.2312.09194","title":"Dyson Equation for Correlated Linearizations and Test Error of Random Features Regression","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Mathematics; Random matrix; Uniqueness; Applied mathematics; Matrix (chemical analysis); Ridge; Scaling; Regression; Linear regression; Class (philosophy); Statistics; Computer science; Eigenvalues and eigenvectors; Mathematical analysis; Artificial intelligence","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":[0.0002477489,0.0001546379,0.0003083333,0.0004682272,0.0001372569,0.00005663733,0.0006412719,0.0002486706,0.000008878426],"category_scores_gemma":[0.001041506,0.0001330029,0.0001380351,0.001480871,0.00008155889,0.0001704704,0.000920242,0.0002072271,0.000008216188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002906934,"about_ca_system_score_gemma":0.0000500267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001573148,"about_ca_topic_score_gemma":0.00002690228,"domain_scores_codex":[0.998894,0.00006218717,0.000186714,0.0006310013,0.00007408,0.0001519558],"domain_scores_gemma":[0.9978521,0.001060422,0.0002925153,0.0005192042,0.0001992924,0.00007649833],"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":[0.0003544153,0.0006568185,0.02992536,0.0004567165,0.0006232018,0.0001228029,0.0006186477,0.6261675,0.000342288,0.3228633,0.006165746,0.0117032],"study_design_scores_gemma":[0.0009930276,0.00009481013,0.009597435,0.00008899945,0.0001832788,8.721068e-7,0.00004006799,0.9550354,0.0001240993,0.03345803,0.0001788752,0.0002051335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02935038,0.00009203886,0.9693432,0.0003217208,0.0002391427,0.0002883129,0.0001454306,0.0001425446,0.00007717474],"genre_scores_gemma":[0.9920553,0.0002624923,0.00341727,0.00001912665,0.0000260023,0.000001653083,0.0002584376,0.000006894968,0.003952844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.965926,"threshold_uncertainty_score":0.5423701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1285123907950168,"score_gpt":0.2276777890962469,"score_spread":0.09916539830123008,"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."}}