{"id":"W4377291682","doi":"10.1016/j.compbiomed.2023.107026","title":"Learning binary and sparse permutation-invariant representations for fast and memory efficient whole slide image search","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Mayo Foundation for Medical Education and Research; Mayo Clinic","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Benchmark (surveying); Deep learning; Generative model; Permutation (music); Binary number; Mathematics; Generative grammar","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":[0.000662593,0.00008357661,0.0001582805,0.0002449853,0.0001862363,0.00002435203,0.0001226762,0.00005561439,0.000001425351],"category_scores_gemma":[0.0001396259,0.00006718373,0.00001133797,0.0003250533,0.0003579524,0.00007376335,0.0001810518,0.0001237843,0.000001893487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001187105,"about_ca_system_score_gemma":0.00002402824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000235985,"about_ca_topic_score_gemma":0.000001327107,"domain_scores_codex":[0.9991488,0.0001046084,0.0001724525,0.0003425772,0.00006003751,0.0001714525],"domain_scores_gemma":[0.9992811,0.0004234804,0.00004220757,0.0001291158,0.00005859595,0.00006547705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009611958,0.000127209,0.01947887,0.0003629062,0.00006272984,0.0001255965,0.02343575,0.0004175371,0.1660118,0.08057728,0.003622406,0.7056818],"study_design_scores_gemma":[0.001629052,0.00075499,0.121758,0.0001520011,0.00001279087,0.00007814175,0.001655319,0.8639039,0.002238089,0.006474157,0.001132518,0.0002110402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1561397,0.0004069596,0.8307863,0.0118415,0.0001872277,0.0003315165,0.00000333464,0.000162221,0.0001412463],"genre_scores_gemma":[0.9692345,0.0006011513,0.02934826,0.0003433353,0.00008619377,0.0000450132,0.0000538664,0.000006931491,0.0002807496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8634863,"threshold_uncertainty_score":0.2739673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03216601874840534,"score_gpt":0.3496567654517432,"score_spread":0.3174907467033379,"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."}}