{"id":"W2925365986","doi":"10.48550/arxiv.1904.00740","title":"Projectron -- A Shallow and Interpretable Network for Classifying Medical Images","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Radon; MNIST database; Computer science; Equidistant; Encoding (memory); Artificial intelligence; Radon transform; Pattern recognition (psychology); Layer (electronics); Image (mathematics); Artificial neural network; Domain (mathematical analysis); Computer vision; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001756656,0.001115738,0.0008339444,0.0008349033,0.0003169015,0.001064135,0.001653128,0.001795962,0.003468313],"category_scores_gemma":[0.004827609,0.0004819457,0.001066257,0.0007855188,0.0007463945,0.002313126,0.001624008,0.001740496,0.001251655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006989904,"about_ca_system_score_gemma":0.0007179388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002415465,"about_ca_topic_score_gemma":0.002697531,"domain_scores_codex":[0.9992484,0.000302834,0.00004263906,0.000153903,0.0001811603,0.00007102104],"domain_scores_gemma":[0.9989441,0.0005485527,0.0001001581,0.0001502206,0.0001966586,0.00006042328],"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":[0.0005064863,0.0001594928,0.004900792,0.000354454,0.0003110213,0.0003374195,0.0002208519,0.3044747,0.01545264,0.01758507,0.01463179,0.6410654],"study_design_scores_gemma":[0.0000135657,0.00008054949,0.0004204852,0.00004127427,0.00002854313,0.000104372,0.0000237355,0.9801515,0.003644098,0.01356702,0.001907763,0.00001697641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02646445,0.0006942657,0.9661281,0.0007367661,0.0001108914,0.00008037694,0.0005141902,0.003149451,0.002121421],"genre_scores_gemma":[0.561029,0.001059708,0.4235287,0.001059156,0.0001918183,0.0003267234,0.002415094,0.0003182175,0.01007167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003468313,"threshold_uncertainty_score":0.01160264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05754061096976197,"score_gpt":0.2060261249360139,"score_spread":0.1484855139662519,"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."}}