{"id":"W4366998711","doi":"10.5539/ells.v13n2p46","title":"An Empirical Study on the Validity of the AES Systems Juku and iWrite for Continuation Writing Task Assessment","year":2023,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Technology-Enhanced Education Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Task (project management); Continuation; Scoring system; Narrative; Grammar; Psychology; Computer science; Mathematics education; Linguistics; Medicine","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":[0.001524351,0.00009850722,0.0001976488,0.00005451088,0.0009374441,0.0001357156,0.0001221267,0.00005837453,6.352456e-7],"category_scores_gemma":[0.001827174,0.00005412101,0.00002988913,0.0004057991,0.0002702979,0.0001079306,0.00007635813,0.0001574707,1.595611e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002795258,"about_ca_system_score_gemma":0.00002390945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002914456,"about_ca_topic_score_gemma":0.0001621016,"domain_scores_codex":[0.998894,0.000362496,0.0001731448,0.0002042363,0.0002075947,0.0001585348],"domain_scores_gemma":[0.9983014,0.001087468,0.0001048938,0.0001750166,0.0003123028,0.00001895845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000004049697,0.00004398868,0.04436857,0.00003284955,0.00007671661,0.000001026704,0.9454744,9.648444e-7,0.0001031758,0.003889148,0.004994873,0.001010205],"study_design_scores_gemma":[0.0001520072,0.0001042759,0.09319901,0.00009070487,0.00003125357,1.517287e-7,0.9020959,0.000007348973,0.00003648204,0.0002065605,0.004013555,0.00006276113],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928496,0.003084743,0.000006592099,0.002067571,0.0005535153,0.0007934312,0.00003971416,0.0001741261,0.0004307048],"genre_scores_gemma":[0.9985452,0.0002227886,0.0000274797,0.00006690715,0.0004353689,0.0002240107,0.00000442699,0.000005925772,0.0004678914],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04883045,"threshold_uncertainty_score":0.7210157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0533578777450666,"score_gpt":0.4335936760121358,"score_spread":0.3802357982670692,"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."}}