{"id":"W7047058070","doi":"","title":"ÉVALUATIONS NATIONALES AU CP EN MATHEMATIQUES EN FRANCE : BIAIS ET IMPACTS SUR LE TRAITEMENT DES DONNEES ISSUES DU DISPOSITIF ÉVALAIDE","year":2025,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"French; Context (archaeology); Data collection; Risk communication","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05354696,0.001104887,0.001665424,0.005788306,0.002040107,0.009902365,0.002116699,0.002366206,0.005020569],"category_scores_gemma":[0.1271636,0.0005249858,0.001296327,0.005987427,0.002337131,0.006812273,0.003488012,0.003417237,0.0009403851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01472246,"about_ca_system_score_gemma":0.01636479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1728911,"about_ca_topic_score_gemma":0.08210542,"domain_scores_codex":[0.9370335,0.02462258,0.002955609,0.004835783,0.02851305,0.002039469],"domain_scores_gemma":[0.8253567,0.06524536,0.007911873,0.01197736,0.08356008,0.005948651],"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":[0.003377966,0.001559799,0.1070519,0.002022379,0.001164375,0.0005017323,0.004253422,0.1377005,0.01477952,0.1159528,0.03473698,0.5768987],"study_design_scores_gemma":[0.000517755,0.002656216,0.2410427,0.001855547,0.0007957796,0.0007285112,0.006205383,0.4903173,0.03393672,0.0275074,0.1940887,0.0003478208],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7826698,0.01677633,0.1104482,0.01582713,0.0009184234,0.0004085402,0.004123479,0.003378023,0.0654501],"genre_scores_gemma":[0.895883,0.00424903,0.07959603,0.0006734026,0.000357467,0.0003783877,0.004646182,0.0005676633,0.01364882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1728911,"threshold_uncertainty_score":0.3437695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01889353606511998,"score_gpt":0.2777986147772354,"score_spread":0.2589050787121154,"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."}}