{"id":"W3002993892","doi":"10.1101/2020.01.21.913624","title":"Deep learning based behavioral analysis enables high precision rodent tracking and is capable of outperforming commercial solutions","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Neuroscience Center Zurich, University of Zurich; Universität Zürich; Olga Mayenfisch Stiftung; Novartis Foundation; McGill University; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Eidgenössische Technische Hochschule Zürich","keywords":"Computer science; Artificial intelligence; Flexibility (engineering); Deep learning; Machine learning; Tracking (education); Set (abstract data type); Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006367863,0.0003575304,0.0005487942,0.0003151695,0.0003085748,0.0001285925,0.0005060397,0.0005428003,0.00005822454],"category_scores_gemma":[0.0004523887,0.0003943455,0.0002477221,0.0007139102,0.0002607902,0.00001383015,0.0008825473,0.0006676324,0.000005329097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009364454,"about_ca_system_score_gemma":0.0004341408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003893356,"about_ca_topic_score_gemma":0.00005148874,"domain_scores_codex":[0.9972708,0.0001671939,0.0005476702,0.0009690116,0.0005201811,0.0005251207],"domain_scores_gemma":[0.9978691,0.00005499936,0.000357296,0.0008075402,0.0005120685,0.0003989601],"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":[0.00005193016,0.0002059066,0.01773949,0.00018126,0.0003930617,0.000004970908,0.00001630105,0.0009765256,0.9801956,0.0000367092,0.0001319359,0.00006624348],"study_design_scores_gemma":[0.0006742335,0.0002632957,0.1505278,0.0001466537,0.0009538725,1.394552e-8,0.00001597375,0.01614287,0.8271771,0.000003286074,0.003442768,0.0006520789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9477961,0.001033641,0.04977784,0.0004705813,0.0000875178,0.0005115443,0.0002642648,0.0000555388,0.000002983829],"genre_scores_gemma":[0.9927257,0.0003816768,0.006330832,0.0001084896,0.0001969022,0.0001719528,0.00001736494,0.00006368342,0.000003440136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1530186,"threshold_uncertainty_score":0.9998509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02579162569987252,"score_gpt":0.2746361755601182,"score_spread":0.2488445498602456,"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."}}