{"id":"W2143183257","doi":"10.1109/cccrv.2004.1301490","title":"Q(Λ)-based image thresholding","year":2004,"lang":"en","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Thresholding; Reinforcement learning; Computer science; Image (mathematics); Exploit; Artificial intelligence; Operator (biology); Binary image; Binary number; Function (biology); Pixel; Image processing; Space (punctuation); Pattern recognition (psychology); Mathematics; Arithmetic; Computer security","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":[0.0000619407,0.00004868463,0.00009772925,0.00005967342,0.00002952629,0.00001478546,0.00002533449,0.00001381317,0.0003024369],"category_scores_gemma":[0.00002924758,0.00003462221,0.00008135784,0.0001301846,0.0000301876,0.00003061515,0.000005496067,0.00005909267,0.000172294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002478799,"about_ca_system_score_gemma":0.00003668959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008862582,"about_ca_topic_score_gemma":0.000001553432,"domain_scores_codex":[0.9996166,0.000002968804,0.00007341643,0.00009829443,0.0001070558,0.0001017246],"domain_scores_gemma":[0.999751,0.00000742536,0.00001239889,0.0001311634,0.00003536466,0.00006269505],"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":[0.0001352143,0.0005840762,0.08171525,0.0001732484,0.0001820445,0.0008681939,0.0001738087,0.0006862025,0.8957905,0.006006178,0.005090395,0.008594917],"study_design_scores_gemma":[0.006028046,0.0003006931,0.02539614,0.0003760202,0.0005102818,0.0001299619,0.0003734586,0.006549199,0.9490258,0.002634097,0.008281026,0.0003952695],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8203041,0.00007247563,0.04660647,0.01944187,0.0000315931,0.00006736473,4.913091e-7,0.0002086357,0.113267],"genre_scores_gemma":[0.9569116,0.000002994436,0.03933776,0.002050576,0.00004922487,0.000001369955,0.000004300462,0.000006859093,0.001635379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1366074,"threshold_uncertainty_score":0.3311472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01312177456208059,"score_gpt":0.2994373423105053,"score_spread":0.2863155677484247,"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."}}