{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07516295,0.001645954,0.001387435,0.001078103,0.001669651,0.001919597,0.002134677,0.001691786,0.004330038],"category_scores_gemma":[0.1745631,0.001147684,0.001457199,0.001027973,0.002313394,0.001378809,0.002329291,0.002250402,0.001933205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003975385,"about_ca_system_score_gemma":0.0007802667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001027339,"about_ca_topic_score_gemma":0.0026256,"domain_scores_codex":[0.9056543,0.05398269,0.01586034,0.008358236,0.01505635,0.001088188],"domain_scores_gemma":[0.8805064,0.06858351,0.005257442,0.02229859,0.02198611,0.001367997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.02206872,0.00412247,0.110082,0.009637157,0.001499973,0.001513696,0.04972447,0.002602656,0.4707309,0.02176433,0.009733772,0.2965199],"study_design_scores_gemma":[0.003255664,0.02550403,0.5026963,0.003044883,0.002274182,0.003902489,0.01878091,0.01220146,0.2469914,0.04134803,0.1385294,0.001471222],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4806601,0.004782969,0.4608575,0.001781865,0.004675109,0.02413659,0.001300327,0.0009548619,0.02085062],"genre_scores_gemma":[0.4066575,0.002361809,0.5173169,0.002365484,0.0008831411,0.06265127,0.001638602,0.0007635795,0.005361748],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.07516295,"threshold_uncertainty_score":0.3975044,"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."}}