{"id":"W3046538170","doi":"10.1111/emip.12382","title":"Synergy and Tension between Large‐Scale and Classroom Assessment: International Trends","year":2020,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Brock University","funders":"","keywords":"Scale (ratio); Test (biology); Political science; Mathematics education; Pedagogy; Sociology; Psychology; Geography; Geology; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001338029,0.0001105199,0.0001332382,0.00005548412,0.0004620808,0.0002840409,0.0001031014,0.00005820222,0.0003935548],"category_scores_gemma":[0.0007046846,0.0001074821,0.00001981759,0.000144964,0.0000912692,0.000678461,0.00007887384,0.0001339768,0.000008068414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006137519,"about_ca_system_score_gemma":0.0001281849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003634855,"about_ca_topic_score_gemma":0.0001217818,"domain_scores_codex":[0.9982424,0.0002485282,0.0001736722,0.0002905626,0.0008713591,0.0001735126],"domain_scores_gemma":[0.9988795,0.0004481317,0.0001217065,0.00005784315,0.0002909317,0.0002019014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001222111,0.0004374725,0.8149075,0.00003774134,0.0003562179,0.000002594953,0.05000371,9.079566e-7,0.0006667293,0.06397557,0.03959125,0.02989812],"study_design_scores_gemma":[0.0003244299,0.00005331112,0.3227398,0.00001653907,0.00007424561,0.000001483268,0.01613181,0.00004029073,0.000003847855,0.0004635765,0.6600313,0.0001193701],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06594703,0.003649217,0.000281559,0.8006032,0.0008205088,0.0002368584,0.00002517447,0.00005304952,0.1283834],"genre_scores_gemma":[0.989265,0.001826033,0.004208669,0.001433643,0.001640826,0.00001379258,0.00004049318,0.000009167736,0.001562389],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.923318,"threshold_uncertainty_score":0.4382993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09632131387335943,"score_gpt":0.4206769110651631,"score_spread":0.3243555971918037,"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."}}