{"id":"W2759176870","doi":"10.19173/irrodl.v18i6.2804","title":"An Evaluation Framework and Instrument for Evaluating e-Assessment Tools","year":2017,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Class (philosophy); Evaluation methods; Empirical research; Human–computer interaction; Multimedia; Management science; Knowledge management; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1581631,0.001599936,0.001323721,0.01165904,0.003749501,0.006737352,0.00271395,0.00264409,0.003693744],"category_scores_gemma":[0.138227,0.000644675,0.002152103,0.007949091,0.003127642,0.007266499,0.004891179,0.00295556,0.001763774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009339133,"about_ca_system_score_gemma":0.0337817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006338591,"about_ca_topic_score_gemma":0.006988918,"domain_scores_codex":[0.8107339,0.1202642,0.02362752,0.003095172,0.04004936,0.002230014],"domain_scores_gemma":[0.8043435,0.065244,0.01153347,0.007260887,0.1087595,0.002858557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005421374,0.002410625,0.03004088,0.004103756,0.0001746401,0.0001578816,0.008622338,0.006894657,0.007582832,0.1552483,0.02792889,0.7562929],"study_design_scores_gemma":[0.001072971,0.01221186,0.1616099,0.02251768,0.0007428243,0.001226698,0.0507094,0.06534863,0.02930218,0.1494219,0.5048837,0.0009523403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04302261,0.002036834,0.7824161,0.005042257,0.0005573193,0.06706591,0.002197637,0.001469108,0.09619223],"genre_scores_gemma":[0.08999264,0.00076258,0.8676165,0.0004889876,0.00004917854,0.03669153,0.001211729,0.0000857554,0.003101006],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1581631,"threshold_uncertainty_score":0.8364567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3896306194989309,"score_gpt":0.6372387545112699,"score_spread":0.247608135012339,"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."}}