{"id":"W4387963612","doi":"10.48550/arxiv.2310.16161","title":"MyriadAL: Active Few Shot Learning for Histopathology","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alberta Innovates","keywords":"Computer science; Artificial intelligence; Machine learning; Oracle; Active learning (machine learning); Encoder; Supervised learning; Data mining; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002659224,0.001362531,0.001622881,0.001863255,0.0007855316,0.001947854,0.004833925,0.003011022,0.004027291],"category_scores_gemma":[0.006181995,0.0009634257,0.001317659,0.00101149,0.001478529,0.002457448,0.003871711,0.003220053,0.002263565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001517253,"about_ca_system_score_gemma":0.001352272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004980811,"about_ca_topic_score_gemma":0.008488449,"domain_scores_codex":[0.9984944,0.0004394196,0.00005417764,0.0005000114,0.0003972669,0.0001147023],"domain_scores_gemma":[0.9980097,0.001035668,0.0001276179,0.0003956158,0.0002735202,0.0001577872],"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":[0.0005386804,0.000376391,0.002008169,0.0004337491,0.0002274643,0.0002637145,0.000315331,0.2243363,0.02082653,0.01734582,0.02822319,0.7051047],"study_design_scores_gemma":[0.00002208091,0.00007139792,0.0002272677,0.00002145233,0.00001567938,0.00009021739,0.00002768188,0.9677715,0.005705573,0.02243212,0.003590817,0.00002412417],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007695416,0.001018213,0.9822235,0.0003947878,0.0001350453,0.0001213629,0.000537772,0.006543027,0.001330957],"genre_scores_gemma":[0.2395175,0.0008998219,0.7406017,0.001484001,0.0003764695,0.0005823416,0.006197442,0.001301582,0.009039147],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004980811,"threshold_uncertainty_score":0.01406348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1218922713489688,"score_gpt":0.2265979497567963,"score_spread":0.1047056784078274,"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."}}