{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00139558,0.0008373975,0.001142693,0.0008383892,0.0003842875,0.0008196633,0.002241953,0.001192753,0.001887524],"category_scores_gemma":[0.004927226,0.0004682067,0.0008918722,0.0006684198,0.001213753,0.002521954,0.002591172,0.001972255,0.0006171612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00099436,"about_ca_system_score_gemma":0.0008257323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001815741,"about_ca_topic_score_gemma":0.001893095,"domain_scores_codex":[0.9994528,0.0001447342,0.0000403215,0.0001486029,0.0001472086,0.00006638876],"domain_scores_gemma":[0.9988453,0.0005003074,0.0001084373,0.000354967,0.0001388469,0.00005208646],"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":[0.0002111519,0.00008206553,0.001376719,0.0001088356,0.00009117275,0.00009984304,0.0001134587,0.559153,0.006773378,0.08045202,0.002896311,0.3486421],"study_design_scores_gemma":[0.000009750434,0.00004203469,0.0000570206,0.000008093128,0.000007892542,0.00002931468,0.000007368483,0.9745607,0.001622842,0.02298915,0.0006602834,0.000005573806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008199542,0.00007905123,0.9898072,0.00007890105,0.00001814037,0.00002577352,0.00003060991,0.0009714217,0.000789455],"genre_scores_gemma":[0.4607413,0.0001737099,0.5346651,0.000278029,0.00006530804,0.0002623452,0.0003326997,0.0003802339,0.003101265],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002241953,"threshold_uncertainty_score":0.007380664,"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."}}