{"id":"W2750181310","doi":"10.5430/wje.v7n4p60","title":"The Most Preferred and Effective Reviewer of L2 Writing among Automated Grading System, Peer Reviewer and Teacher","year":2017,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Computer science; Mathematics education; Psychology; Medical education; Medicine; 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":[],"consensus_categories":[],"category_scores_codex":[0.001936596,0.00007868544,0.0001832617,0.0001047629,0.0004349176,0.0001780976,0.0003868986,0.00003105845,0.00000152148],"category_scores_gemma":[0.001170585,0.00005266985,0.00003231324,0.0001217853,0.0001211426,0.0005083474,0.00008157159,0.0001930486,5.899853e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006325966,"about_ca_system_score_gemma":0.0001426833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001104248,"about_ca_topic_score_gemma":0.000007031213,"domain_scores_codex":[0.9991006,0.0001349749,0.0003687447,0.000116252,0.0001859611,0.00009352885],"domain_scores_gemma":[0.9975823,0.0001978328,0.0009560921,0.0003069179,0.0009092814,0.00004763645],"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":[0.00001453111,0.0002800152,0.3487502,0.0007506501,0.0001948825,0.000002365527,0.002041982,0.000003655605,0.000499016,0.1012862,0.0400106,0.5061659],"study_design_scores_gemma":[0.0001856221,0.00005119273,0.985292,0.002983336,0.00005815017,0.00006484196,0.0007094565,0.0009146424,0.0002800979,0.001808653,0.0075496,0.0001024686],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9569494,0.02209801,0.001243968,0.01253614,0.003479604,0.0006015055,6.173971e-7,0.00005201187,0.003038747],"genre_scores_gemma":[0.9954188,0.0004736203,0.003266392,0.00002841257,0.000175064,0.00001808761,3.589495e-7,0.000004083862,0.0006151544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6365418,"threshold_uncertainty_score":0.3345078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01613487927259164,"score_gpt":0.3315316042400074,"score_spread":0.3153967249674158,"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."}}