{"id":"W3036003990","doi":"10.1109/jbhi.2020.3003643","title":"Tenodesis Grasp Detection in Egocentric Video","year":2020,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Craig H. Neilsen Foundation","keywords":"GRASP; Computer science; Computer vision; Artificial intelligence; Human–computer interaction; Computer graphics (images)","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":[0.0005880035,0.00006464443,0.0003181834,0.0002795777,0.00003611055,0.000009188164,0.000035464,0.00007569572,0.00002269255],"category_scores_gemma":[0.0002348439,0.00004288989,0.00006727935,0.0002816842,0.00006158341,0.0001179137,0.000007599644,0.0003090507,0.000007649087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009523397,"about_ca_system_score_gemma":0.0002528506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000908404,"about_ca_topic_score_gemma":0.000002238218,"domain_scores_codex":[0.9984046,0.00002426609,0.001056152,0.00003360612,0.0003298884,0.0001514855],"domain_scores_gemma":[0.998903,0.00008044644,0.0003629074,0.00003531605,0.0000756388,0.0005426859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006005573,0.0003240933,0.03200925,0.004217075,0.00007575277,0.00004632481,0.01245184,0.00001761829,0.0005145204,0.00002245577,0.01346482,0.9362557],"study_design_scores_gemma":[0.02023674,0.01879445,0.6221589,0.002502914,0.0001526508,0.002881476,0.01285066,0.04482915,0.001152345,0.0004182996,0.2735808,0.0004415932],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9247577,0.001076899,0.01850597,0.05458169,0.0006761845,0.0002415797,0.000003820677,0.00001492256,0.0001412919],"genre_scores_gemma":[0.984284,0.002511356,0.003707396,0.009120178,0.0003610983,7.668622e-7,0.000001169613,0.000004516476,0.000009562124],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9358141,"threshold_uncertainty_score":0.1748999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0352531382607448,"score_gpt":0.315603790082136,"score_spread":0.2803506518213912,"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."}}