{"id":"W2156770411","doi":"10.1177/0265532209104666","title":"Interacting in pairs in a test of oral proficiency: Co-constructing a better performance","year":2009,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":163,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Test (biology); Psychology; Meaning (existential); Context (archaeology); Negotiation; Social psychology; Mathematics education","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008745365,0.00007059228,0.0001284538,0.0001686429,0.00009090579,0.00002749879,0.0001334796,0.00004145074,0.00005734649],"category_scores_gemma":[0.006404143,0.00007187673,0.00001720052,0.0006446068,0.00007185568,0.0001782217,0.00001146488,0.0002035043,0.000005524333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007201653,"about_ca_system_score_gemma":0.0001842248,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007276883,"about_ca_topic_score_gemma":0.001565743,"domain_scores_codex":[0.9990702,0.00007881753,0.0002915865,0.000133915,0.000136962,0.0002885158],"domain_scores_gemma":[0.9990865,0.0006114139,0.0001418829,0.00008159674,0.00003845003,0.00004018604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001628253,0.00004121177,0.6462628,0.00001222895,2.976236e-7,0.000004617653,0.1330892,0.0000109161,0.002875242,0.00005682594,0.000002569546,0.2176425],"study_design_scores_gemma":[0.0007903318,0.0001270993,0.7268726,0.001049932,0.000005274872,0.00001463379,0.2554966,0.008204082,0.006666456,0.0001019732,0.0002691103,0.0004019037],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9365197,0.00002648729,0.000001658372,0.0003017929,0.00005918647,0.0001288944,7.818629e-7,0.00004161773,0.06291988],"genre_scores_gemma":[0.9940374,8.091318e-7,0.005483535,0.0002789349,0.00009623174,0.000003649228,0.000001073518,0.00000451924,0.00009381247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2172406,"threshold_uncertainty_score":0.9993337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06423787690980926,"score_gpt":0.4414124951436066,"score_spread":0.3771746182337974,"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."}}