{"id":"W4400728577","doi":"10.2139/ssrn.4897693","title":"Automated Writing Evaluation for Second Language Placement Testing","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Language assessment; Natural language processing; Linguistics; Programming language; Psychology; Mathematics education; Philosophy","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":[0.001840535,0.00102345,0.0009373007,0.00242713,0.0004883047,0.001631284,0.001134986,0.000990238,0.01842947],"category_scores_gemma":[0.01615126,0.0003091128,0.0003590165,0.0009533605,0.0002299424,0.0009792892,0.001287314,0.0006869301,0.006471573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004185808,"about_ca_system_score_gemma":0.001072932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002283761,"about_ca_topic_score_gemma":0.003064047,"domain_scores_codex":[0.9958407,0.00161191,0.0003846395,0.0005577145,0.001410117,0.0001949088],"domain_scores_gemma":[0.973855,0.01461889,0.001207097,0.002258991,0.00705945,0.001000522],"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":[0.002058238,0.001170544,0.01542399,0.0002599712,0.0000495512,0.0003573005,0.0003986059,0.004035518,0.04498858,0.0006557585,0.01290468,0.9176973],"study_design_scores_gemma":[0.001282627,0.005637831,0.1225611,0.0002935145,0.0002541184,0.003020774,0.001911442,0.6687455,0.1604837,0.005499022,0.03011718,0.0001931701],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7025319,0.001045898,0.2492272,0.0004639709,0.0004378672,0.001079584,0.003228205,0.02260612,0.01937921],"genre_scores_gemma":[0.8504626,0.0001901139,0.1285799,0.0001325148,0.00008965642,0.000421057,0.003061704,0.0005533193,0.01650928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01842947,"threshold_uncertainty_score":0.06165266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02801840690808603,"score_gpt":0.3603164728257328,"score_spread":0.3322980659176467,"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."}}