{"id":"W1996738877","doi":"10.1016/j.asoc.2006.12.003","title":"A reinforcement agent for threshold fusion","year":2007,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reinforcement; Reinforcement learning; Fusion; Artificial intelligence; Mathematical optimization; Mathematics; Materials science; Composite material","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":[0.001268658,0.0001319179,0.0001410645,0.0001003586,0.0002155398,0.00009603909,0.0005815566,0.00005782212,0.00001179931],"category_scores_gemma":[0.00003765163,0.0001269856,0.00005698495,0.0002317559,0.00003376101,0.0001010259,0.0003768041,0.0001130922,0.0000248529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007572231,"about_ca_system_score_gemma":0.00002968595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000042659,"about_ca_topic_score_gemma":8.575268e-7,"domain_scores_codex":[0.9984666,0.00000650945,0.0004004128,0.0003541898,0.0003675853,0.0004047],"domain_scores_gemma":[0.999071,0.0002473912,0.0001468868,0.0003619786,0.00006217266,0.0001105619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000145035,0.00005018138,0.0000388151,0.00004775644,0.00001415866,0.000007018347,0.00116128,0.0004588111,0.02730818,0.06751961,0.005246634,0.898133],"study_design_scores_gemma":[0.00204341,0.0002555609,0.000499956,0.0001186149,0.00001726032,0.00001417747,0.0002897554,0.4699758,0.5030161,0.01255076,0.01042448,0.0007940545],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001931183,0.00002033618,0.9911121,0.0001272423,0.0002202104,0.000632523,2.052629e-7,0.0006151565,0.005341101],"genre_scores_gemma":[0.4605578,0.000001493764,0.5368704,0.002386126,0.000088814,0.00001580655,0.000005653808,0.000008821105,0.00006510165],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.897339,"threshold_uncertainty_score":0.5178325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02370262743590369,"score_gpt":0.2998350591602246,"score_spread":0.2761324317243209,"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."}}