{"id":"W4386723774","doi":"10.22190/jtesap230220007g","title":"INVESTIGATING THE CONSTRUCT OF AERONAUTICAL ENGLISH LISTENING TESTING: A QUALITATIVE ANALYSIS OF THE ICAO RATING SCALE","year":2023,"lang":"en","type":"article","venue":"Journal of Teaching English for Specific and Academic Purposes","topic":"Air Traffic Management and Optimization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Construct (python library); Aviation; Civil aviation; Active listening; Context (archaeology); Scale (ratio); CLARITY; Rating scale; Psychology; Language assessment; Benchmarking; Air traffic control; Construct validity; Test (biology); Applied psychology; Engineering; Computer science; Psychometrics; Business; Geography; Mathematics education; Marketing; Communication; Developmental psychology","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":[0.002333813,0.0001356424,0.0003932584,0.000249213,0.000199608,0.00003713036,0.0003246305,0.00009154369,0.000003042295],"category_scores_gemma":[0.003596868,0.00008646367,0.0001882371,0.0008021542,0.0002228741,0.0002201512,0.00007584399,0.0007302102,5.427559e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002781612,"about_ca_system_score_gemma":0.00002130297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002436374,"about_ca_topic_score_gemma":0.000001297844,"domain_scores_codex":[0.9984176,0.000154242,0.0008153331,0.0001131049,0.0003121459,0.0001875755],"domain_scores_gemma":[0.9971426,0.001872489,0.0005619921,0.0001181787,0.0002542918,0.00005046484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004164755,0.00003674582,0.02975469,0.0006564773,0.001823735,0.000001555948,0.2542795,0.6502405,0.005290362,0.01709946,0.01257077,0.02820458],"study_design_scores_gemma":[0.001459537,0.0001965704,0.01228631,0.00134064,0.002161816,0.000009203279,0.2012346,0.7690232,0.002110085,0.00192113,0.00777243,0.000484502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988748,0.0005639393,0.008174108,0.0001606082,0.000542325,0.00023053,0.00002301598,0.00008624927,0.001471205],"genre_scores_gemma":[0.9885379,0.0001307297,0.01088831,0.00001843765,0.0003537954,0.000004330866,0.000005288216,0.00001877624,0.00004243308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1187827,"threshold_uncertainty_score":0.4306047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03864989528926189,"score_gpt":0.3017960680157423,"score_spread":0.2631461727264804,"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."}}