{"id":"W3157861089","doi":"10.1371/journal.pcbi.1008914","title":"WormPose: Image synthesis and convolutional networks for pose estimation in C. elegans","year":2021,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"Okinawa Institute of Science and Technology Graduate University; University of Toronto; Vrije Universiteit Amsterdam","keywords":"Pose; Computer science; Artificial intelligence; Convolutional neural network; Leverage (statistics); Python (programming language); Computer vision; Robustness (evolution); Deep learning; 3D pose estimation; Pattern recognition (psychology); Machine learning; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001169456,0.0001168431,0.0001484135,0.00004410145,0.0000726823,0.0000210051,0.00007199286,0.0001485192,0.00002075498],"category_scores_gemma":[0.0002265084,0.000128314,0.00004253292,0.00005907918,0.0001119026,0.000004736462,0.00006486649,0.00006397234,0.000002753791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001602777,"about_ca_system_score_gemma":0.000102119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005871468,"about_ca_topic_score_gemma":0.0000278372,"domain_scores_codex":[0.9991407,0.00007731369,0.0002045337,0.0003308899,0.00005480092,0.0001917623],"domain_scores_gemma":[0.9994662,0.0001579801,0.00005708393,0.0001010007,0.000170301,0.00004739972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003111574,0.0007144397,0.03744884,0.0001513869,0.0004005233,0.00001570022,0.0003365088,0.3597713,0.5734397,0.01591064,0.002335311,0.009164418],"study_design_scores_gemma":[0.001611063,0.0003045701,0.05340863,0.00003586101,0.00007330716,0.0000956407,0.00006888773,0.855099,0.06289133,0.02420773,0.001648265,0.0005557758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6310856,0.0007494796,0.3670251,0.0007250475,0.0001140172,0.0001614325,0.00007010136,0.00001191152,0.00005729536],"genre_scores_gemma":[0.9431407,0.00007516688,0.05498114,0.0004374047,0.0001430757,0.00004667546,0.001110415,0.0000140445,0.00005137072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5105484,"threshold_uncertainty_score":0.5232491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01035283138669751,"score_gpt":0.2464443058992276,"score_spread":0.2360914745125301,"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."}}