{"id":"W3037473509","doi":"10.48550/arxiv.2004.12209","title":"Convex Representation Learning for Generalized Invariance in\\n Semi-Inner-Product Space","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Regular polygon; Representation (politics); Euclidean geometry; Generality; Invariant (physics); Mathematical optimization; Euclidean space; Kernel (algebra); Regularization (linguistics); Applied mathematics; Algebra over a field; Computer science; Artificial intelligence; Pure mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001191582,0.0007552726,0.00103593,0.0005791713,0.0006103368,0.0005346372,0.002130253,0.0004440587,0.000160761],"category_scores_gemma":[0.001233051,0.001047826,0.0004829048,0.002666057,0.0002721685,0.001196933,0.001731772,0.001890154,0.0002380106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005049645,"about_ca_system_score_gemma":0.000688805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005081918,"about_ca_topic_score_gemma":0.00009639427,"domain_scores_codex":[0.9931449,0.001159799,0.0008079391,0.003651083,0.0002911618,0.000945064],"domain_scores_gemma":[0.995658,0.0006543164,0.001222863,0.001423797,0.00056806,0.0004729926],"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":[0.0003789659,0.00008877899,0.008829761,0.0002400423,0.0001199693,0.0002610311,0.002983422,0.8093628,0.001274983,0.1741009,0.0002689871,0.00209037],"study_design_scores_gemma":[0.003295592,0.0001528959,0.004069337,0.0002144192,0.0001224069,0.000008050439,0.0008776258,0.9623173,0.0007030464,0.0176065,0.009574084,0.001058781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08750476,0.0001783044,0.9039918,0.002367924,0.001486183,0.001482749,0.000008484095,0.0003073696,0.00267241],"genre_scores_gemma":[0.9762896,0.0007819826,0.01271314,0.0004181403,0.0003713838,0.00001114609,0.0001031962,0.00007301008,0.009238357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8912787,"threshold_uncertainty_score":0.9991972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1483503063517345,"score_gpt":0.2319144239418398,"score_spread":0.08356411759010532,"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."}}