{"id":"W1712156565","doi":"10.3968/j.css.1923669720130901.2201","title":"Empirical Reforms on New-CET4 Communicative Listening Test","year":2013,"lang":"en","type":"article","venue":"Canadian social science","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Active listening; Conversation; Dictation; Test (biology); Sentence; Empirical research; College English; Section (typography); Key (lock); Psychology; Informational listening; Linguistics; Computer science; Mathematics education; Listening comprehension; Speech recognition; Natural language processing; Epistemology; Communication","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001950234,0.0001017605,0.0001370562,0.000154052,0.002159016,0.0004662428,0.0006635249,0.00002418352,0.0026649],"category_scores_gemma":[0.0002458883,0.00007684547,0.00005715193,0.0002101609,0.002193747,0.0004008269,0.00007996766,0.000153148,0.0005904536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003905954,"about_ca_system_score_gemma":0.0003926797,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1250563,"about_ca_topic_score_gemma":0.3824098,"domain_scores_codex":[0.9989353,0.0000182627,0.0001247176,0.0001993844,0.0002741568,0.000448187],"domain_scores_gemma":[0.9991636,0.00007040746,0.0000548534,0.000229808,0.0001674984,0.0003138146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001106359,0.00003750641,0.004022605,0.000002816595,0.00003505559,0.000008591629,0.2857702,4.777448e-7,0.00004077852,0.4832973,0.2021178,0.02466581],"study_design_scores_gemma":[0.0001513679,0.00007660085,0.007858706,0.00002935034,0.00002708351,7.540343e-7,0.224437,0.00005050307,0.00003405595,0.004754509,0.7621735,0.00040653],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01757012,0.00004871249,8.670737e-7,0.007192585,0.0001375182,0.00009139367,0.0000155836,0.00002824846,0.974915],"genre_scores_gemma":[0.9745886,0.00000294561,0.00003831836,0.003418642,0.0005701734,0.00001218262,0.000003115675,0.000007403919,0.02135859],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9570185,"threshold_uncertainty_score":0.99914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05095865714753748,"score_gpt":0.316410164032927,"score_spread":0.2654515068853895,"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."}}