{"id":"W4220991108","doi":"10.1214/22-ejs1998","title":"Adaptive threshold-based classification of sparse high-dimensional data","year":2022,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Random Matrices and Applications","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Classifier (UML); Pattern recognition (psychology); Sample size determination; Binary classification; Feature (linguistics); Binary number; Diagonal; Covariance matrix; Linear classifier; Algorithm; Covariance; Artificial intelligence; Statistics; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.000986538,0.00009591996,0.0002634852,0.0001080923,0.0001377928,0.00000969606,0.0005165756,0.00002295944,0.0002472798],"category_scores_gemma":[0.0001403007,0.00008713689,0.0000449491,0.000223581,0.00005009504,0.00007355583,0.00009226926,0.00042883,0.000002289638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001707467,"about_ca_system_score_gemma":0.0007940043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001192211,"about_ca_topic_score_gemma":0.0000182279,"domain_scores_codex":[0.9983772,0.00008632908,0.0006039312,0.0001315544,0.0005721942,0.0002287586],"domain_scores_gemma":[0.9977347,0.0005920939,0.0009786075,0.0004033182,0.000243423,0.00004786909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000328569,0.0004737943,0.0000573193,0.00002642624,0.000126087,0.000008058065,0.00006437282,0.004054324,0.001024506,0.963944,0.0279275,0.001965063],"study_design_scores_gemma":[0.002999573,0.001062257,0.0006305917,0.00002383021,0.0004069267,0.00007547958,0.0002599255,0.132219,0.0003805904,0.8568233,0.004915782,0.0002027204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1285806,0.0007768649,0.8671973,0.0008291121,0.0001814728,0.0003655785,0.001839492,0.00001629297,0.0002132507],"genre_scores_gemma":[0.9387816,0.0000387513,0.06087896,0.00003237126,0.00006576364,0.000007567983,0.0001027714,0.00001808621,0.00007419013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8102009,"threshold_uncertainty_score":0.3553339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07747682503576564,"score_gpt":0.3228351643396283,"score_spread":0.2453583393038627,"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."}}