{"id":"W3215221635","doi":"10.48550/arxiv.2111.11646","title":"CytoImageNet: A large-scale pretraining dataset for bioimage transfer learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Transfer of learning; Artificial intelligence; Scale (ratio); Machine learning; Pattern recognition (psychology); Cartography","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":[0.001516619,0.003497762,0.001077747,0.002593707,0.001081605,0.001897302,0.005086782,0.003234713,0.01415537],"category_scores_gemma":[0.005689799,0.001112513,0.001538291,0.002331219,0.001070759,0.002361551,0.002404328,0.004025689,0.01815232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002337944,"about_ca_system_score_gemma":0.002611766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01152515,"about_ca_topic_score_gemma":0.02167491,"domain_scores_codex":[0.9991398,0.0001030378,0.00005685633,0.0003834033,0.0002275807,0.0000893543],"domain_scores_gemma":[0.9980466,0.0005158387,0.0001174325,0.0006770405,0.0004687883,0.0001742639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004971023,0.0007064432,0.003689892,0.001300059,0.0002183104,0.0004525028,0.0001404786,0.0320902,0.02855368,0.008449436,0.7102361,0.2136659],"study_design_scores_gemma":[0.0004998737,0.0005347388,0.010768,0.0003978866,0.0001661008,0.001467758,0.000234178,0.4867936,0.09747379,0.03991255,0.361517,0.000234556],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.07334244,0.004411303,0.328385,0.003940301,0.001523738,0.001922379,0.3656593,0.1908371,0.0299784],"genre_scores_gemma":[0.07861521,0.001333662,0.2549568,0.001025559,0.0001841049,0.002289619,0.6445237,0.004794628,0.0122766],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01415537,"threshold_uncertainty_score":0.04735452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03846914609253699,"score_gpt":0.2193104096411394,"score_spread":0.1808412635486024,"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."}}