{"id":"W2020408370","doi":"10.1167/8.6.271","title":"Getting the most out of classification images","year":2010,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bonferroni correction; Thresholding; Pattern recognition (psychology); Artificial intelligence; Computer science; Pixel; Mathematics; Contextual image classification; Observer (physics); Statistical hypothesis testing; Image processing; Image (mathematics); Statistics","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":[0.0007867148,0.00005417607,0.0001188707,0.00008467177,0.00004987926,0.00003041304,0.00009598832,0.00008251295,0.00002167655],"category_scores_gemma":[0.0001471165,0.00003237752,0.00007074767,0.0001029927,0.00001667651,0.0001462841,0.000008639161,0.0003640903,0.000008571307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001464199,"about_ca_system_score_gemma":0.00001359192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003610936,"about_ca_topic_score_gemma":0.000002495002,"domain_scores_codex":[0.9992561,0.0000284834,0.0004024647,0.0000360168,0.0002109079,0.00006596568],"domain_scores_gemma":[0.9993572,0.00008791179,0.0002427328,0.0001192368,0.0001642817,0.00002859671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001100903,0.000007856244,0.0001272675,0.000009388334,0.000009161402,9.036316e-7,0.0001215242,0.0003769261,0.9417073,0.00003164011,0.003772749,0.0538243],"study_design_scores_gemma":[0.00209435,0.0008551354,0.1725259,0.0005988354,0.0001052989,0.0002977678,0.001611976,0.0407645,0.645197,0.0005898632,0.1349519,0.0004075751],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890473,0.0001094191,0.004513604,0.0001764547,0.003693885,0.00007397802,0.000001535561,0.00001977799,0.002364003],"genre_scores_gemma":[0.9990264,0.00001835572,0.0002738847,0.0000070349,0.0006276442,4.290564e-7,2.1604e-7,0.000009261897,0.00003672847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2965103,"threshold_uncertainty_score":0.1581811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01981616565201014,"score_gpt":0.276992776660468,"score_spread":0.2571766110084578,"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."}}