{"id":"W4367592383","doi":"10.58379/homq5772","title":"Exploring shared and individual assessment of paired oral interactions","year":2022,"lang":"en","type":"article","venue":"Studies in Language Assessment","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Rubric; Psychology; Task (project management); Variation (astronomy); Modality (human–computer interaction); Audiology; Cognitive psychology; Computer science; Medicine; Artificial intelligence; Mathematics education","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":[0.000768922,0.0001213394,0.0002553964,0.0001785073,0.0005304935,0.00005245612,0.0001215545,0.000006601103,0.0009040879],"category_scores_gemma":[0.0000455749,0.0001129356,0.00004532537,0.00005941715,0.0001249146,0.0002344356,0.0004427721,0.0004450447,6.453278e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001683363,"about_ca_system_score_gemma":0.00003493149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004829704,"about_ca_topic_score_gemma":0.000750738,"domain_scores_codex":[0.9987779,0.0002675606,0.0002750384,0.0002017184,0.0002878354,0.0001899827],"domain_scores_gemma":[0.9994713,0.0002078408,0.0001236703,0.0001409248,0.00003196018,0.00002431195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001482843,0.0003812729,0.02952866,0.0001582327,0.0005140806,0.00008424769,0.904093,0.0005080926,0.0001762413,0.03894755,0.001758743,0.02383508],"study_design_scores_gemma":[0.0006283572,0.0002639533,0.03493162,0.00009970079,0.00005517793,0.000005481365,0.9327574,0.0004106492,0.000009327338,0.0001234323,0.03051106,0.0002038626],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9778717,0.0008324748,0.00001787189,0.0003161829,0.0008714101,0.0001623977,0.00005986465,0.00006103499,0.01980709],"genre_scores_gemma":[0.9973499,0.00005220014,0.001064009,0.00008328466,0.0001273338,0.0002771828,0.0000338347,0.00001490579,0.0009973133],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03882412,"threshold_uncertainty_score":0.9899129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3685810683728511,"score_gpt":0.4261905241132528,"score_spread":0.05760945574040166,"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."}}