{"id":"W2104280957","doi":"10.1167/5.9.1","title":"Accurate statistical tests for smooth classification images","year":2005,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Toolbox; Artificial intelligence; Pattern recognition (psychology); Computer science; MATLAB; Statistical hypothesis testing; Field (mathematics); Statistical analysis; Computation; Variety (cybernetics); Machine learning; Mathematics; Statistics; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0006006595,0.00007585077,0.0001312431,0.000116871,0.00007525517,0.0001573033,0.0004396599,0.00004652654,0.00001265929],"category_scores_gemma":[0.0002663225,0.00005582856,0.00006910091,0.0001606885,0.00003238415,0.0008902541,0.00003603968,0.0001153837,0.00001644749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006370797,"about_ca_system_score_gemma":0.00007985917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.916298e-7,"about_ca_topic_score_gemma":2.02728e-7,"domain_scores_codex":[0.9990108,0.00004337352,0.0004138415,0.000127046,0.0002792053,0.0001257613],"domain_scores_gemma":[0.9986719,0.0002287938,0.0003815917,0.0001931844,0.0004444604,0.0000800401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000435121,0.0001770263,0.00004401386,0.00001505941,0.000007369193,0.000003485376,0.0000711898,0.00000588584,0.1177074,0.02817371,0.0238886,0.8298628],"study_design_scores_gemma":[0.002037328,0.002559824,0.2158267,0.0002197112,0.00005133667,0.0002053478,0.00007237541,0.2232486,0.1947032,0.03521077,0.3253063,0.0005585114],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008747552,0.0001355674,0.9925824,0.005857829,0.0001200714,0.0001002577,0.000004442671,0.00004321951,0.0002814065],"genre_scores_gemma":[0.6157159,0.0001008499,0.383666,0.0001835585,0.000181568,0.000003034958,0.000001563943,0.000005661715,0.0001418526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8293042,"threshold_uncertainty_score":0.2276623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03938048048456388,"score_gpt":0.3650808678566028,"score_spread":0.3257003873720389,"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."}}