{"id":"W2513844773","doi":"10.1017/s0272263115000418","title":"METHODOLOGICAL CHOICES IN RATING SPEECH SAMPLES","year":2015,"lang":"en","type":"article","venue":"Studies in Second Language Acquisition","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Fluency; German; Psychology; Pronunciation; Rating scale; Intelligibility (philosophy); Active listening; Linguistics; Audiology; Cognitive psychology; Developmental psychology; Mathematics education; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002204284,0.0001238435,0.0003203998,0.000205914,0.00004101501,0.00001380372,0.0001697625,0.0001354066,0.002190825],"category_scores_gemma":[0.0006894934,0.0001057732,0.00003316484,0.0003004025,0.0001868251,0.00006602334,0.000153218,0.0003165619,0.0001162014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008843705,"about_ca_system_score_gemma":0.00001798309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005289278,"about_ca_topic_score_gemma":0.002312941,"domain_scores_codex":[0.9980874,0.0007961161,0.0002882969,0.0003234991,0.0001324823,0.0003722142],"domain_scores_gemma":[0.9986595,0.0009386148,0.00006383329,0.0002273241,0.00005917653,0.00005158802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001077235,0.0007883559,0.1263217,0.0002049019,0.000447271,0.003790386,0.7339817,0.00005956414,0.03707396,0.004301163,0.01930948,0.07264426],"study_design_scores_gemma":[0.005641269,0.0008251107,0.6124567,0.0001490157,0.0000210805,0.0001930651,0.343359,0.00005654173,0.00835852,0.0254795,0.002788972,0.0006712493],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9647264,0.0177782,0.0000345569,0.0001640649,0.0005704239,0.0001810158,0.00001514178,0.0000285047,0.01650165],"genre_scores_gemma":[0.9961145,0.00005964393,0.002133034,0.0005626655,0.0002295897,0.00007781651,0.00002311685,0.00001045562,0.0007891739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4861349,"threshold_uncertainty_score":0.9987213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4005620098617411,"score_gpt":0.5195403514319998,"score_spread":0.1189783415702587,"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."}}