{"id":"W7095589736","doi":"","title":"Knowledge and Skills Related to the Development and Use of Teacher-Made Tests","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Test (biology); Recall; Standardized test; Knowledge level; Quarter (Canadian coin)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003905647,0.00005159766,0.00007090066,0.00003572356,0.0001889162,0.00003396282,0.00008717291,0.0000383382,0.0001324326],"category_scores_gemma":[0.000186906,0.00002512667,0.000009459236,0.0001503041,0.000114198,0.0001095865,0.00008543101,0.00002434032,0.00003873359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002322241,"about_ca_system_score_gemma":0.00005262218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008342549,"about_ca_topic_score_gemma":0.002907057,"domain_scores_codex":[0.9994634,0.00005739806,0.000116552,0.0001090619,0.0001259412,0.0001276401],"domain_scores_gemma":[0.9994618,0.0003454108,0.00002661098,0.00006456183,0.00003640914,0.00006521926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004602619,0.0000879279,0.8072971,0.00000312249,0.00003194595,2.978572e-7,0.07259034,3.387988e-8,0.0007791687,0.02547894,0.005344377,0.08838221],"study_design_scores_gemma":[0.0001792731,0.00001671829,0.7522333,0.00002745367,0.00000557541,1.273097e-7,0.002014949,4.605346e-7,0.000265386,0.0001238906,0.2450648,0.00006805221],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9419577,0.00007427381,0.00002354116,0.002282329,0.00006294661,0.0001847002,4.284659e-7,0.00002069443,0.05539344],"genre_scores_gemma":[0.9226,0.00007232046,0.001008077,0.00003320418,0.00001853729,0.000005797533,1.368031e-7,0.000003148718,0.07625882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2397204,"threshold_uncertainty_score":0.1622206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0336801024578597,"score_gpt":0.3461971084290518,"score_spread":0.3125170059711921,"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."}}