{"id":"W4321376664","doi":"10.1080/10904018.2022.2164718","title":"DOES VIDEO BELONG IN L2 ACADEMIC LISTENING TESTS? STAKEHOLDERS’ PERCEPTIONS ABOUT TEST DIFFICULTY, AUTHENTICITY, AND MOTIVATION","year":2023,"lang":"en","type":"article","venue":"International Journal of Listening","topic":"Communication in Education and Healthcare","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Paragon Testing Enterprises; British Council; National Federation of Modern Language Teachers Associations; Educational Testing Service","keywords":"Active listening; Psychology; Perception; Test (biology); Social psychology; Applied psychology; Cognitive psychology; Communication","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009782398,0.0001996983,0.0002223775,0.0007866754,0.001663376,0.004524442,0.0004829634,0.001207908,0.003683983],"category_scores_gemma":[0.04955707,0.0002163575,0.0002861155,0.0003192304,0.001602615,0.002716987,0.002587519,0.001217006,0.0003799932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001323916,"about_ca_system_score_gemma":0.001477305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003536126,"about_ca_topic_score_gemma":0.003817613,"domain_scores_codex":[0.9922593,0.00456353,0.0003194083,0.0003058277,0.001688374,0.0008635384],"domain_scores_gemma":[0.9724577,0.01642113,0.00404617,0.0004474825,0.002919886,0.003707593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000574274,0.0007252161,0.4693612,0.0004332512,0.00005557162,0.002597051,0.4102645,0.0003248529,0.0129229,0.003016955,0.002086061,0.09763806],"study_design_scores_gemma":[0.000025171,0.0009347699,0.242638,0.0003597204,0.00004542777,0.001346734,0.734683,0.001097487,0.002642411,0.001763844,0.01437176,0.0000917311],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933469,0.0000950069,0.0005560197,0.001051797,0.00002029935,0.00002318404,0.00001328495,0.000005933256,0.004887624],"genre_scores_gemma":[0.9993319,0.00006393472,0.0001349159,0.0001284417,0.000008885057,0.00001275373,0.00001076396,0.000003784094,0.0003045246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009782398,"threshold_uncertainty_score":0.05173492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1099192116525557,"score_gpt":0.4251381891406588,"score_spread":0.3152189774881031,"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."}}