{"id":"W2916875281","doi":"10.7202/1055896ar","title":"Digital assessment of mathematics: Opportunities, issues and criteria","year":2019,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Plea; Test (biology); Computer science; Mathematics education; Management science; Mathematics; Engineering; Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003033965,0.00007559542,0.0001245735,0.00008420079,0.0000296293,0.0001663611,0.0001315842,0.00003297687,0.00005804381],"category_scores_gemma":[0.00009846572,0.00006981652,0.00002278485,0.00006668115,0.000008665942,0.0006794031,0.00004606715,0.00005707396,0.00001765947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004897981,"about_ca_system_score_gemma":0.0001687646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002023644,"about_ca_topic_score_gemma":0.00000111045,"domain_scores_codex":[0.9989366,0.0002945212,0.0002387366,0.000160705,0.0002934199,0.0000760516],"domain_scores_gemma":[0.9992473,0.0001665933,0.0001688871,0.0002180406,0.0001775989,0.00002155762],"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":[0.000001126359,0.0001575971,0.02041241,0.0002471843,0.00004154634,6.096354e-7,0.07528304,0.0003210109,0.00505344,0.8672377,0.0005293695,0.03071498],"study_design_scores_gemma":[0.0006765924,0.0004677447,0.6389477,0.0007401832,0.00003537639,0.00003132458,0.01300748,0.2636237,0.003070447,0.01140691,0.06730022,0.0006923466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4861847,0.0001011536,0.4935501,0.002010516,0.0009141795,0.0003664243,0.000003293675,0.00007262239,0.01679701],"genre_scores_gemma":[0.9698067,0.00001764251,0.01893331,0.0000280548,0.00004076165,0.00000880749,0.00001668259,0.00000634871,0.01114169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8558308,"threshold_uncertainty_score":0.2847035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09385667342878277,"score_gpt":0.3813391217940354,"score_spread":0.2874824483652526,"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."}}