{"id":"W4404307587","doi":"10.48550/arxiv.2410.18933","title":"Confidence is detection-like in high-dimensional spaces","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Immune Systems Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; UK Research and Innovation; HORIZON EUROPE Framework Programme; Government of the United Kingdom; Canadian Institute for Advanced Research","keywords":"Confidence interval; Computer science; Mathematics; Statistics","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001110668,0.0002383732,0.0002484129,0.0003035607,0.00005994402,0.0000567922,0.0003036541,0.0002640747,0.00009316793],"category_scores_gemma":[0.000007497268,0.0003050596,0.00009904601,0.0004883091,0.00006566396,0.00007476924,0.0004293956,0.0006728754,0.0009093792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003018264,"about_ca_system_score_gemma":0.00006202207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001780246,"about_ca_topic_score_gemma":0.001051,"domain_scores_codex":[0.9989195,0.00003128395,0.0002251212,0.0005382653,0.00006414644,0.0002216071],"domain_scores_gemma":[0.999212,0.00005401982,0.0000553708,0.0005531594,0.0000578057,0.00006760455],"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":[0.000008432372,0.00002124245,0.0002449223,0.0002245405,0.0001068713,0.0001075293,0.0003250944,0.9621988,0.002645142,0.03289182,0.00103196,0.00019365],"study_design_scores_gemma":[0.0001924846,0.00001353298,0.001132823,0.000359167,0.00009959665,0.00000669856,0.0002345551,0.9090299,0.005117001,0.08087009,0.002282358,0.0006618189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9753392,0.0003859648,0.02013809,0.00006304158,0.001492687,0.0003756639,0.00004220665,0.0005261651,0.001636948],"genre_scores_gemma":[0.9979736,0.00005899122,0.00005188944,0.0000188139,0.00007226739,0.000006098015,0.00001042339,0.00004150978,0.001766459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05316892,"threshold_uncertainty_score":0.9999402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03828340695604669,"score_gpt":0.1765385522441644,"score_spread":0.1382551452881177,"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."}}