{"id":"W3092500786","doi":"10.47670/wuwijar201821lh","title":"Direct assessment of second language writing: Holistic and analytic scoring","year":2018,"lang":"en","type":"article","venue":"Westcliff International Journal of Applied Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wycliffe College","funders":"","keywords":"Rubric; Writing assessment; Language assessment; Task (project management); Test (biology); Mathematics education; Standards-based assessment; Reliability (semiconductor); Peer assessment; Psychology; Educational assessment; Computer science","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":[0.01975202,0.0008770516,0.001470841,0.008483659,0.0008798594,0.003278912,0.00128498,0.0006562821,0.002819428],"category_scores_gemma":[0.05976461,0.0004355397,0.0009237697,0.004952458,0.002391607,0.00344912,0.00401563,0.001037231,0.001016103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001605703,"about_ca_system_score_gemma":0.003717713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001185569,"about_ca_topic_score_gemma":0.004146059,"domain_scores_codex":[0.9732018,0.007825904,0.002864161,0.001127312,0.01468286,0.0002980835],"domain_scores_gemma":[0.9673738,0.01152868,0.004439313,0.001664513,0.01414482,0.0008489033],"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":[0.0001878981,0.0001794755,0.03056622,0.001740201,0.00008286125,0.00007692548,0.003467667,0.0004864152,0.004184648,0.006701717,0.002870318,0.9494557],"study_design_scores_gemma":[0.0004048041,0.007045375,0.6145904,0.01319069,0.0007307819,0.009585685,0.03596938,0.03504802,0.03738033,0.09386154,0.1512913,0.0009017129],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3625289,0.02816862,0.4531199,0.003364226,0.001368008,0.006220174,0.0009538882,0.00162769,0.1426485],"genre_scores_gemma":[0.5214506,0.01236416,0.4524756,0.0004500325,0.0002344486,0.003603106,0.0005139617,0.0001608508,0.008747091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01975202,"threshold_uncertainty_score":0.1044599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09942307377488162,"score_gpt":0.5055932593544762,"score_spread":0.4061701855795946,"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."}}