{"id":"W4379258954","doi":"10.48550/arxiv.2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Naval Research; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Reproducing kernel Hilbert space; Representation (politics); Feature learning; Generalization; Artificial intelligence; Computer science; Mathematics; Laplace operator; Statistical learning theory; Algorithm; Regression; Machine learning; Applied mathematics; Mathematical optimization; Hilbert space; 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":[0.0002489362,0.0002980471,0.0002596566,0.0004384801,0.0004142615,0.0001836532,0.000580683,0.0002404408,0.000005011122],"category_scores_gemma":[0.00004285278,0.0003412395,0.0001140309,0.001041224,0.00007156466,0.0007319775,0.0007828661,0.0006068362,0.00001501114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003884172,"about_ca_system_score_gemma":0.00006851395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003902624,"about_ca_topic_score_gemma":0.00001663106,"domain_scores_codex":[0.9978092,0.0002922818,0.0002380685,0.001190728,0.0001702868,0.000299405],"domain_scores_gemma":[0.9983964,0.0003587715,0.0003879039,0.0006292907,0.00009570439,0.0001319578],"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":[0.00003588989,0.00003053066,0.007179569,0.000111638,0.00004407662,0.00009616465,0.0004340091,0.9688261,0.0001838098,0.0220389,0.00008720342,0.0009321461],"study_design_scores_gemma":[0.0006253652,0.00003931421,0.0008981948,0.000161127,0.00004052042,0.000001786437,0.0002253749,0.9184314,0.0001870168,0.07907172,0.000006855988,0.0003113211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06687973,0.00002058696,0.9309458,0.0002169936,0.0004134435,0.0004304025,0.000001835455,0.0009455404,0.0001456998],"genre_scores_gemma":[0.981718,0.0001525324,0.01770085,0.00005536935,0.00004966544,0.000003524802,0.00008238106,0.00003053186,0.0002071416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9148383,"threshold_uncertainty_score":0.999904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2031581300810819,"score_gpt":0.2336139396656635,"score_spread":0.03045580958458155,"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."}}