{"id":"W2067457676","doi":"10.1136/bmj.38993.466678.be","title":"Putting the cart before the horse: testing to improve learning","year":2007,"lang":"en","type":"article","venue":"BMJ","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Worry; Psychology; Context (archaeology); Social psychology; Test (biology); Cognitive psychology; Applied psychology; Mathematics education; History","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004233623,0.0000664556,0.00006462713,0.00001998135,0.001468073,0.000157604,0.0003417248,0.00003811373,0.00003584192],"category_scores_gemma":[0.001450182,0.00003773902,0.00004052859,0.0004009641,0.00009050152,0.00007105392,0.0001102456,0.0001962392,0.00008590157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005123048,"about_ca_system_score_gemma":0.00005287334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001126958,"about_ca_topic_score_gemma":0.003064749,"domain_scores_codex":[0.9988468,0.00009461209,0.0001527751,0.0001306453,0.000404807,0.000370412],"domain_scores_gemma":[0.9991968,0.0004610195,0.00008312371,0.0001254371,0.00007652829,0.00005707225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004493805,0.0000159445,0.6179948,0.000003616849,0.00002441155,0.000007958409,0.08899954,0.00004554262,0.001132518,0.008629972,0.008766907,0.2743743],"study_design_scores_gemma":[0.0001431724,0.00008865797,0.6036889,0.000028244,0.0000238378,0.000001429384,0.1291565,0.0001071675,0.00007201971,0.0007297288,0.2658379,0.0001224869],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6213578,0.0000444953,0.0002621766,0.02606158,0.00085265,0.0008186098,4.15706e-7,0.0001252281,0.3504771],"genre_scores_gemma":[0.9881201,7.639156e-7,0.001098607,0.0004056697,0.002126563,0.00001678912,3.644995e-7,0.000008194603,0.008222932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3667623,"threshold_uncertainty_score":0.9998319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03700351524578259,"score_gpt":0.383076420799716,"score_spread":0.3460729055539334,"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."}}