{"id":"W2990689782","doi":"10.5753/cbie.sbie.2019.199","title":"Avaliação de Juízes: Um Modelo Estatístico para Perfilação de Avaliadores","year":2019,"lang":"pt","type":"article","venue":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Bureau for International Education","keywords":"Concordance; Competence (human resources); Statistics; Psychology; Mathematics; Computer science; Social psychology; Medicine","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","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.01523138,0.002083419,0.002459155,0.001412106,0.001232696,0.003205744,0.005989725,0.001613575,0.01707882],"category_scores_gemma":[0.007865026,0.001832546,0.001581949,0.002443928,0.0009960536,0.002737124,0.001711303,0.002543133,0.01817003],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002226763,"about_ca_system_score_gemma":0.006275301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001777553,"about_ca_topic_score_gemma":0.0001201177,"domain_scores_codex":[0.9798973,0.001436259,0.004408868,0.002775084,0.006364209,0.005118287],"domain_scores_gemma":[0.9846067,0.004262511,0.001682395,0.004970495,0.001617745,0.00286009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001228443,0.002826472,0.5936267,0.001054445,0.0007809999,0.000150631,0.02626781,0.0125107,0.003999447,0.002983502,0.2269749,0.1275959],"study_design_scores_gemma":[0.01041246,0.004904083,0.3046045,0.00387247,0.001916995,0.0006154871,0.05351387,0.4213139,0.009353657,0.03080658,0.1491499,0.009536167],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9566788,0.003147206,0.01420116,0.003494554,0.004672976,0.003199806,0.0005192597,0.0003598914,0.01372634],"genre_scores_gemma":[0.9623288,0.002266592,0.005167703,0.006670224,0.0005766393,0.0001935167,0.00009998245,0.000219855,0.02247672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4088032,"threshold_uncertainty_score":0.9997581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0738775683116693,"score_gpt":0.35990389654442,"score_spread":0.2860263282327506,"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."}}