{"id":"W4387829999","doi":"10.32612/uw.25449354.2023.1.pp.14-39","title":"Investigating the Construct of a Listening Test to Assess Pilots’ Comprehension: a Step-by-Step Project for Test Developers","year":2023,"lang":"en","type":"article","venue":"Applied Linguistics Papers","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Construct (python library); Active listening; Test (biology); Context (archaeology); Isolation (microbiology); Computer science; Language assessment; Perspective (graphical); Psychology; Mathematics education; Artificial intelligence; Communication","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":[0.102186,0.001743087,0.0009647235,0.002210981,0.002945425,0.005111149,0.003576668,0.002326461,0.003044914],"category_scores_gemma":[0.102625,0.001049334,0.001137594,0.0007867628,0.004221561,0.005226969,0.00838119,0.005768702,0.001540879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003538254,"about_ca_system_score_gemma":0.02507342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004044519,"about_ca_topic_score_gemma":0.004542652,"domain_scores_codex":[0.9531386,0.03500623,0.00217182,0.001789692,0.006198864,0.001694902],"domain_scores_gemma":[0.8781543,0.04775336,0.005050665,0.01304491,0.04243039,0.01356644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006817316,0.0173517,0.03971916,0.00152777,0.0001431504,0.001727624,0.04888945,0.006119903,0.04263311,0.01664761,0.01491977,0.809639],"study_design_scores_gemma":[0.002983331,0.06901532,0.1323684,0.009919235,0.0008645344,0.007249297,0.1931673,0.05400731,0.1783787,0.0524698,0.2986833,0.0008934074],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4243796,0.0007713553,0.4872727,0.008541102,0.0006030459,0.06158793,0.0004903448,0.001276517,0.01507746],"genre_scores_gemma":[0.1843537,0.0004834112,0.7891774,0.0008207589,0.00006344871,0.01954689,0.0006282954,0.000340655,0.004585339],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.102186,"threshold_uncertainty_score":0.5404175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08292959112814333,"score_gpt":0.2992895023522449,"score_spread":0.2163599112241016,"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."}}