{"id":"W2919446416","doi":"10.18162/ritpu.2009.159","title":"10.18162/ritpu.2009.159","year":2016,"lang":"fr","type":"dataset","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Pencil (optics); Multiple choice; Test (biology); Significant difference; Psychology; Cognition; Mathematics education; Computer science; Statistics; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001988745,0.001652069,0.001243547,0.007330793,0.0006324364,0.003347918,0.001793305,0.001114254,0.3913777],"category_scores_gemma":[0.007816743,0.0008706254,0.001637739,0.007870062,0.0002739718,0.001087541,0.00219727,0.001055276,0.4804615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009425146,"about_ca_system_score_gemma":0.001778127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006570111,"about_ca_topic_score_gemma":0.009607628,"domain_scores_codex":[0.9990588,0.0001786841,0.0001792144,0.0002518656,0.0002183312,0.0001131333],"domain_scores_gemma":[0.9974706,0.0008370264,0.0003145742,0.0008597465,0.0003155826,0.0002023772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002631963,0.0001343212,0.006671561,0.00235851,0.0002344959,0.000078062,0.00006682814,0.0003960918,0.0004514029,0.0006720125,0.9218591,0.06681448],"study_design_scores_gemma":[0.000517486,0.00007117105,0.009238606,0.0006482637,0.0001337527,0.0001863028,0.000061806,0.0007439741,0.0005502931,0.0007697492,0.987049,0.0000295919],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001308762,0.0004589198,0.0005613776,0.0001649246,0.0000970157,0.00006741867,0.986568,0.002811117,0.007962536],"genre_scores_gemma":[0.002971744,0.0004533735,0.001879367,0.0001394639,0.0000478717,0.0002575248,0.9817758,0.0005962393,0.01187875],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.6086223,"threshold_uncertainty_score":0.8681258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03289347138127198,"score_gpt":0.3469420268414372,"score_spread":0.3140485554601652,"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."}}