{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003999704,0.001072747,0.001204542,0.0008290159,0.0003760895,0.001461584,0.001557893,0.001792507,0.001738594],"category_scores_gemma":[0.02064465,0.0006817556,0.000701166,0.0007306809,0.002709605,0.004136778,0.002744766,0.003129647,0.0006272729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001135541,"about_ca_system_score_gemma":0.001240134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001797275,"about_ca_topic_score_gemma":0.001942418,"domain_scores_codex":[0.9982948,0.0008160126,0.0000620775,0.0003148341,0.000415922,0.00009632714],"domain_scores_gemma":[0.9840752,0.01127225,0.001135177,0.002232467,0.001006504,0.0002783347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001443816,0.0001131495,0.001784693,0.0002288253,0.00006984776,0.00007608681,0.000235796,0.8126558,0.006503264,0.1030945,0.003009829,0.07208382],"study_design_scores_gemma":[0.000004169491,0.00002191301,0.0001607821,0.000009410656,0.000003226914,0.00001096597,0.000007686176,0.9697471,0.0009130229,0.02882441,0.0002905058,0.000006944292],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01963674,0.0003448916,0.9776778,0.0005504875,0.00003080215,0.00003455406,0.00008223345,0.0005203786,0.001122053],"genre_scores_gemma":[0.653632,0.001194051,0.3387535,0.000540961,0.0002762621,0.0003063696,0.0008040664,0.0004691912,0.004023546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003999704,"threshold_uncertainty_score":0.02115273,"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."}}