{"id":"W3130803020","doi":"10.48550/arxiv.1809.00082","title":"NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Feature (linguistics); Feature vector; Algorithm; Computer science; Invariant (physics); Artificial intelligence; Representation (politics); Pattern recognition (psychology); Euclidean space; Function (biology); Mathematics; 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":[0.0004573698,0.0003469057,0.0004485598,0.0003037117,0.0002865103,0.000257562,0.001893369,0.0003737499,0.00003997621],"category_scores_gemma":[0.0001077726,0.0003592623,0.0004322111,0.000602499,0.0001029717,0.0005929187,0.001258692,0.0005590902,0.00006985473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001655499,"about_ca_system_score_gemma":0.0002334446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00028054,"about_ca_topic_score_gemma":0.00003951985,"domain_scores_codex":[0.997471,0.0002959875,0.0001888745,0.001576047,0.0001331396,0.0003349817],"domain_scores_gemma":[0.9969686,0.0002113557,0.0004399102,0.001865913,0.000350856,0.0001633141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001774634,0.0004233332,0.000788636,0.0002578819,0.003814367,0.0003879903,0.001128795,0.06061915,0.000157051,0.8434826,0.04874939,0.04001335],"study_design_scores_gemma":[0.0005326532,0.00008745072,0.0006236255,0.00001910361,0.0008363801,0.000006520865,0.00004775924,0.9624233,0.0000933285,0.0192066,0.01571407,0.0004092182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001480699,0.00005728189,0.994146,0.001015599,0.0007054221,0.0005195915,0.000130044,0.0003735023,0.001571844],"genre_scores_gemma":[0.7242873,0.0002145696,0.2525485,0.0003842443,0.0007376006,0.00001118664,0.00123791,0.00006913178,0.02050962],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9018041,"threshold_uncertainty_score":0.9998859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1291869983052002,"score_gpt":0.2375083733548435,"score_spread":0.1083213750496433,"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."}}