{"id":"W2084189123","doi":"10.2310/7070.2001.20148","title":"Reliability of the Sunnybrook Facial Grading System by Novice Users","year":2001,"lang":"en","type":"article","venue":"The Journal of Otolaryngology","topic":"Facial Rejuvenation and Surgery Techniques","field":"Medicine","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Intraclass correlation; Intra-rater reliability; Grading (engineering); Medicine; Inter-rater reliability; Reliability (semiconductor); Physical therapy; Confidence interval; Rating scale; Psychology; Psychometrics; Clinical psychology; Developmental psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.001536785,0.00009012304,0.0003626695,0.00008276811,0.00008888168,0.000004009678,0.0002499759,0.0001031621,0.00005801911],"category_scores_gemma":[0.0005003287,0.00004542587,0.0001829732,0.0002280235,0.0001902011,0.00007260672,0.00003794856,0.00037473,0.000003983285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001093683,"about_ca_system_score_gemma":0.0001166588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007519412,"about_ca_topic_score_gemma":0.000008422847,"domain_scores_codex":[0.9986022,0.0003437658,0.0005431515,0.00006544458,0.0002936544,0.0001518023],"domain_scores_gemma":[0.9987,0.0002615324,0.0004362717,0.0002548085,0.0002821159,0.00006525563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002567122,0.0003888965,0.6900643,0.000192465,0.0002284605,0.0001157764,0.001761709,0.00003417197,0.2585283,0.001826892,0.04033444,0.003957423],"study_design_scores_gemma":[0.002784052,0.001281907,0.4980219,0.0006360197,0.0004557665,0.009501939,0.001371065,0.000532041,0.07126199,0.0006049581,0.4132687,0.0002795761],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911824,0.0001432331,0.0005550383,0.004788203,0.000318389,0.0002069473,0.000002811301,0.00002027281,0.002782661],"genre_scores_gemma":[0.9985714,0.00009820656,0.00008838068,0.0009447121,0.00004379875,0.000001454876,6.334726e-7,0.000008829526,0.0002425676],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3729343,"threshold_uncertainty_score":0.1852413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01285392577351509,"score_gpt":0.264272408184553,"score_spread":0.2514184824110379,"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."}}