{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003829947,0.0003841867,0.000408144,0.0001450716,0.0001808355,0.0001094522,0.000628005,0.0005128433,0.00009919422],"category_scores_gemma":[0.00008095911,0.0004889645,0.0004824503,0.0002135326,0.0001114773,0.00001524092,0.0008562438,0.0004793603,0.000006205182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004878681,"about_ca_system_score_gemma":0.0001705079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000431715,"about_ca_topic_score_gemma":0.0002468012,"domain_scores_codex":[0.9976315,0.0001590397,0.0002431405,0.001443698,0.00006923889,0.000453367],"domain_scores_gemma":[0.9984272,0.00002600535,0.0001143187,0.001098533,0.0002039539,0.0001300156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006541363,0.0008311753,0.00823878,0.0009460647,0.002280084,0.0006279955,0.0008527972,0.06582936,0.8894988,0.0002394824,0.02760369,0.002397609],"study_design_scores_gemma":[0.003472613,0.0006794623,0.00056155,0.0002941987,0.002095164,0.00002664623,0.002748691,0.1583949,0.6346975,0.0005012699,0.1934312,0.003096878],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4224367,0.000303918,0.5751432,0.00001540658,0.00004216831,0.0003863082,0.0009082902,0.0000630783,0.0007009616],"genre_scores_gemma":[0.9669185,0.0007531713,0.003972978,0.0001597574,0.000154989,0.000008970461,0.02603494,0.00006936196,0.00192736],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5711702,"threshold_uncertainty_score":0.9997562,"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."}}