{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02789833,0.00005730585,0.0001522195,0.0000440871,0.00122425,0.001040702,0.001061513,0.0000350422,0.0001603991],"category_scores_gemma":[0.008503228,0.000043081,0.00002366734,0.00008839908,0.0002693996,0.0005786929,0.000457337,0.0002824901,0.000001011265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001557968,"about_ca_system_score_gemma":0.0003286534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009219456,"about_ca_topic_score_gemma":0.0001236619,"domain_scores_codex":[0.9973083,0.0008738188,0.0002372316,0.0001936089,0.00120054,0.0001864737],"domain_scores_gemma":[0.9977074,0.001246877,0.0002106466,0.0001942482,0.0005839184,0.00005693845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00008636638,0.0001150549,0.3203178,0.0003610938,0.00005133462,7.57357e-7,0.001624002,0.00002830239,0.00008289883,0.1741043,0.0003557751,0.5028723],"study_design_scores_gemma":[0.002618124,0.0005793917,0.8084773,0.01487752,0.00006852728,0.000001301858,0.03906668,0.028277,0.00002498131,0.06363035,0.04210627,0.0002725576],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.884092,0.006932979,0.001777344,0.05619396,0.0003748853,0.006236644,0.00005796477,0.00001380364,0.04432046],"genre_scores_gemma":[0.9833716,0.01426625,0.001808796,0.00006339503,0.00007963085,0.0002579571,0.00006723528,0.000003895337,0.00008121451],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5025997,"threshold_uncertainty_score":0.9999963,"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."}}