{"id":"W2145055698","doi":"10.1177/0265532210368717","title":"Explaining ESL essay holistic scores: A multilevel modeling approach","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Educational Testing Service","keywords":"Psychology; Argumentation theory; Context (archaeology); Multilevel model; Set (abstract data type); Multilevel modelling; Social psychology; Epistemology; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006918146,0.0002151494,0.0002137296,0.0001198984,0.0008408013,0.0003802165,0.0002492951,0.00006621973,0.0003535916],"category_scores_gemma":[0.002272333,0.0001906683,0.00006203242,0.00004895132,0.00009599784,0.0002241068,0.00008060793,0.001038103,0.00006712238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002022778,"about_ca_system_score_gemma":0.00004769389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00190087,"about_ca_topic_score_gemma":0.0002490589,"domain_scores_codex":[0.9986669,0.00007160731,0.0002718268,0.0003442783,0.00021134,0.0004340002],"domain_scores_gemma":[0.9989648,0.000447406,0.0001148494,0.0002964509,0.00007893623,0.00009749181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001272887,0.0001495046,0.002585647,0.0002176799,0.00004208168,0.00009398563,0.8471537,0.01300773,0.008911178,0.05369629,0.0001106889,0.07401884],"study_design_scores_gemma":[0.0003722018,0.00002909834,0.00006990362,0.0001830618,0.00003059929,0.00003521718,0.04492009,0.9527322,0.00003440423,0.0003272926,0.0008539393,0.0004119936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8514761,0.000141738,0.008339768,0.00001759399,0.0004266923,0.0001099715,0.000007719938,0.0006814672,0.1387989],"genre_scores_gemma":[0.9679496,2.161449e-7,0.02734209,0.0001550435,0.001756844,0.00002280277,0.00002715376,0.0000608441,0.00268538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9397244,"threshold_uncertainty_score":0.7775228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1195594706556013,"score_gpt":0.2960164806540859,"score_spread":0.1764570099984846,"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."}}