{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02200349,0.0005074794,0.0005830491,0.001239937,0.001260642,0.008312287,0.001713885,0.006858469,0.007765641],"category_scores_gemma":[0.1592012,0.0002355478,0.0005106975,0.001272442,0.01391561,0.01344716,0.003993242,0.002398211,0.00312213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001978002,"about_ca_system_score_gemma":0.002152281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002128653,"about_ca_topic_score_gemma":0.001551163,"domain_scores_codex":[0.9745287,0.01867059,0.001388212,0.001126988,0.003627227,0.0006582043],"domain_scores_gemma":[0.8947385,0.06898447,0.01021183,0.0117403,0.01184553,0.002479385],"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":[0.0005025006,0.0001923012,0.01157331,0.001640352,0.00004442863,0.0006280883,0.007916719,0.001306646,0.001040654,0.3738993,0.07177553,0.5294803],"study_design_scores_gemma":[0.000098599,0.000611426,0.01407318,0.004501973,0.00005348923,0.004073869,0.01011038,0.004250779,0.004577594,0.4987196,0.458683,0.0002460746],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.06086471,0.0442939,0.202416,0.4365586,0.009349105,0.0003765712,0.0002907814,0.001501815,0.2443484],"genre_scores_gemma":[0.8903748,0.01115524,0.04776008,0.02983895,0.003187762,0.0005211259,0.0002918577,0.0001669793,0.01670326],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.02200349,"threshold_uncertainty_score":0.1163669,"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."}}