{"id":"W2951082895","doi":"10.1038/s41598-019-38748-8","title":"Explaining the unique nature of individual gait patterns with deep learning","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Gait Recognition and Analysis","field":"Engineering","cited_by":255,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; Deutsche Forschungsgemeinschaft","keywords":"Gait; Relevance (law); Black box; Variable (mathematics); Deep learning; Gait analysis; Biomechanics","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":[],"consensus_categories":[],"category_scores_codex":[0.0006659431,0.00008920307,0.0001259168,0.0001225688,0.00009675552,0.0001316852,0.0001098221,0.00006274256,0.0003753772],"category_scores_gemma":[0.00002623916,0.00005804267,0.00005956121,0.0003784395,0.0000461511,0.00009994429,0.00002844269,0.0003134925,0.00001777518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000106046,"about_ca_system_score_gemma":0.00001594768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004017392,"about_ca_topic_score_gemma":0.00002564762,"domain_scores_codex":[0.99901,0.00002630232,0.0002152792,0.0002214997,0.0003683121,0.0001585802],"domain_scores_gemma":[0.99943,0.0000307079,0.0001077156,0.0003121132,0.00008025706,0.00003920425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009983994,0.00007522959,0.7265132,0.0003715104,0.0006363911,0.0004149981,0.01077986,0.1887693,0.02973221,0.0002716056,0.003052987,0.0393727],"study_design_scores_gemma":[0.001792516,0.0003651074,0.318446,0.002082696,0.0009209096,0.002222462,0.04396418,0.1218789,0.3261212,0.003171277,0.1758932,0.003141641],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932405,0.00008112054,0.0008449593,0.00001733195,0.0008864378,0.00009286181,0.000001246695,0.00008639508,0.004749129],"genre_scores_gemma":[0.9987999,0.000003537434,0.0001466461,0.00001545838,0.00001979379,0.000006061322,0.00005494579,0.00001414197,0.000939548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4080673,"threshold_uncertainty_score":0.4110117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005678345017782112,"score_gpt":0.1986532522106385,"score_spread":0.1929749071928564,"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."}}