{"id":"W3207282779","doi":"10.1080/10904018.2021.1941028","title":"VISUALS IN THE ASSESSMENT AND TESTING OF SECOND LANGUAGE LISTENING: A METHODOLOGICAL SYNTHESIS","year":2021,"lang":"en","type":"article","venue":"International Journal of Listening","topic":"Subtitles and Audiovisual Media","field":"Arts and Humanities","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Active listening; Psychology; Data collection; Construct (python library); Coding (social sciences); Process (computing); Computer science; Data science; Sociology; Social science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001081202,0.00006213327,0.0001907448,0.00009022748,0.00003680497,0.0001295482,0.0001838437,0.00002067111,0.0006616594],"category_scores_gemma":[0.001375332,0.00003954821,0.00007299946,0.00003383653,0.00006957283,0.0001198381,0.00005284543,0.0001744345,6.276716e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002258657,"about_ca_system_score_gemma":0.00005321015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002449869,"about_ca_topic_score_gemma":0.00007912447,"domain_scores_codex":[0.9989555,0.0002103747,0.0003770454,0.00007093925,0.0003095647,0.00007652627],"domain_scores_gemma":[0.9969323,0.002384366,0.0003047629,0.00004609999,0.0003097051,0.00002279705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002424774,0.0009700167,0.1056247,0.0002613941,0.001224738,0.006343609,0.3357269,0.0001322928,0.1312321,0.1475382,0.00162864,0.2690749],"study_design_scores_gemma":[0.003954609,0.001212276,0.3266751,0.004732088,0.0004417819,0.005852398,0.502916,0.002359478,0.04199737,0.008480391,0.1004185,0.0009600358],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822256,0.0004923322,0.00009669506,0.0007085788,0.0003946047,0.00002309781,0.000008427185,0.000002933322,0.01604772],"genre_scores_gemma":[0.9930679,0.00001425856,0.005884537,0.0002377621,0.000543508,0.000001687874,0.000001053922,0.000005103616,0.0002441949],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2681149,"threshold_uncertainty_score":0.7244706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1847205064042924,"score_gpt":0.4089476310886315,"score_spread":0.2242271246843391,"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."}}