{"id":"W2082333579","doi":"10.1017/s0958344000001014","title":"<i>Can computerised testing be authentic?</i>","year":2000,"lang":"en","type":"article","venue":"ReCALL","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Authentic assessment; Computer science; Field (mathematics); Process (computing); Portfolio; Context (archaeology); Computerized adaptive testing; Test (biology); Software testing; Multimedia; Software engineering; Software; Psychology; Pedagogy; Programming language; Psychometrics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002834315,0.00007107625,0.00009965428,0.00002083202,0.0003316463,0.0001094333,0.000229772,0.00005113399,0.001878637],"category_scores_gemma":[0.000036861,0.00006991761,0.00004272129,0.0002362477,0.00009109287,0.00007424556,0.00002228023,0.00007514389,0.0001833891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004095233,"about_ca_system_score_gemma":0.00005521619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000541691,"about_ca_topic_score_gemma":0.0001930454,"domain_scores_codex":[0.999081,0.00008283697,0.0001207491,0.0001521305,0.0002894279,0.0002738719],"domain_scores_gemma":[0.9996077,0.0001309402,0.00003063293,0.0001007384,0.00003367671,0.00009626966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003916611,0.0004644222,0.1447595,0.00002240649,0.00008745387,0.00004853164,0.07085568,0.00003227281,0.0009943765,0.01576078,0.05056449,0.7163709],"study_design_scores_gemma":[0.0007224476,0.00008430008,0.05664584,0.00004989505,0.00003180318,0.000001361729,0.001806272,0.0006994781,0.00004226758,0.002161158,0.9373612,0.0003939106],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5394382,0.00002339117,0.00002786007,0.00357158,0.0002407204,0.0001473532,0.000002187759,0.0001721841,0.4563765],"genre_scores_gemma":[0.971581,0.00004093011,0.002902682,0.0008403726,0.0004787956,0.000005848047,0.000003911301,0.00001012869,0.02413633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8867968,"threshold_uncertainty_score":0.9990338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04836833027328086,"score_gpt":0.3304791017577502,"score_spread":0.2821107714844694,"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."}}