{"id":"W3046671975","doi":"10.1017/s1431927620015548","title":"Learning Biology Through Puzzle-solving: Unbiased Automatic Understanding of Microscopy Images with Self-supervised Learning","year":2020,"lang":"en","type":"article","venue":"Microscopy and Microanalysis","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Centre for Phenogenomics; University of Toronto","funders":"","keywords":"Computer science; Microscopy; Artificial intelligence; Content (measure theory); Machine learning; Mathematics; Physics; Optics","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":[0.0002813956,0.000396263,0.0007066488,0.0001503082,0.0003451453,0.0001040594,0.0002962208,0.0002238793,0.00008975025],"category_scores_gemma":[0.0001307173,0.0003623803,0.0002636082,0.0006157283,0.0003361673,0.00002598942,0.0002258523,0.0003252164,0.000005025689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004444677,"about_ca_system_score_gemma":0.00006477697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001343973,"about_ca_topic_score_gemma":0.00002884329,"domain_scores_codex":[0.9978257,0.0002664636,0.0005275591,0.0008177653,0.0001268199,0.0004356306],"domain_scores_gemma":[0.9989401,0.00005747555,0.0003756752,0.0003567602,0.0001402767,0.0001297721],"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":[0.00009649495,0.00006180724,0.01876136,0.000145301,0.0008440269,0.000006630824,0.001016324,0.00008023241,0.9780903,0.000009237131,0.0004666237,0.0004216051],"study_design_scores_gemma":[0.0008430892,0.0007302013,0.00007847424,0.00005330068,0.0008348187,0.00001315525,0.001729541,0.002091832,0.9886061,0.00002624499,0.004566646,0.0004265934],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8693542,0.002703454,0.1266658,0.0002570636,0.000009175582,0.0002275677,0.00001014289,0.000146822,0.0006257066],"genre_scores_gemma":[0.9524976,0.00145199,0.04517979,0.0003144863,0.00005206296,0.00001265729,0.0002419288,0.00006035707,0.0001891229],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08314337,"threshold_uncertainty_score":0.9998828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01394649981822681,"score_gpt":0.2711943848055963,"score_spread":0.2572478849873695,"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."}}