{"id":"W2280732594","doi":"","title":"Gestion et émasculation des évaluations : le cas du Canada","year":2011,"lang":"fr","type":"article","venue":"Docs.school Publications","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":true,"confidence":"low","status":"direct model label, unvalidated"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"low","status":"direct model label, unvalidated"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005785437,0.0002960753,0.0002805677,0.0005118143,0.00132499,0.0006814849,0.000784511,0.0002296262,0.0255619],"category_scores_gemma":[0.006542417,0.0002960198,0.0001541877,0.002403502,0.0002793365,0.003810545,0.0001425912,0.0004829676,0.001673669],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00111358,"about_ca_system_score_gemma":0.01383352,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5283992,"about_ca_topic_score_gemma":0.8204929,"domain_scores_codex":[0.994643,0.001074655,0.001168179,0.0006810753,0.001903033,0.0005300662],"domain_scores_gemma":[0.9937908,0.0008497621,0.0005175491,0.001184079,0.003074149,0.0005836331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001440919,0.0006229713,0.1215838,0.00002299444,0.0001036879,0.000002395783,0.006185686,0.00428954,0.00006446592,0.5220945,0.2518866,0.09312894],"study_design_scores_gemma":[0.000392746,0.00003771621,0.5995156,0.00003044307,0.00006209438,0.00002398239,0.001309874,0.02486695,0.00006438852,0.02173873,0.3516964,0.0002610608],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1328483,0.003336491,0.1206248,0.3165683,0.005020431,0.00203513,0.0004417711,0.0003169244,0.4188078],"genre_scores_gemma":[0.9368448,0.0006682203,0.01190269,0.001936493,0.0003964549,0.000378617,0.0004011237,0.00003400711,0.04743754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8039966,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2524109226161727,"score_gpt":0.4428439298136063,"score_spread":0.1904330071974336,"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."}}