{"id":"W4383069305","doi":"10.1177/02655322231179134","title":"Fairness of using different English accents: The effect of shared L1s in listening tasks of the Duolingo English test","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Active listening; Psychology; Stress (linguistics); Test (biology); Interlanguage; Vocabulary; Dictation; Linguistics; Task (project management); Hindi; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008786324,0.0001458727,0.0003815934,0.0001429863,0.00006970653,0.00001457166,0.0006334386,0.0001137518,0.00007897416],"category_scores_gemma":[0.009390903,0.00008804037,0.00009271014,0.001026229,0.0001571846,0.00003172339,0.0003855859,0.0004250576,0.000001841431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002391685,"about_ca_system_score_gemma":0.00002439923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00161162,"about_ca_topic_score_gemma":0.0001456935,"domain_scores_codex":[0.9983354,0.0004021143,0.0004349853,0.0002219876,0.0002315361,0.0003740347],"domain_scores_gemma":[0.9947923,0.004171662,0.0002871632,0.0005583448,0.0001597648,0.00003075531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004835302,0.00007894072,0.8246284,0.0004663288,0.00005442847,0.00002409659,0.0846558,0.0002144238,0.08812476,0.00001681029,0.00003569039,0.001652003],"study_design_scores_gemma":[0.001350578,0.0002277478,0.9487026,0.001034373,0.0000666193,0.000006415669,0.006844816,0.003722264,0.03784671,0.00004536225,0.000004057939,0.0001484726],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.997453,0.0002652556,0.000003578032,0.00001367124,0.0003868962,0.0003732477,0.0000648381,0.00004614301,0.0013934],"genre_scores_gemma":[0.9997041,0.000001449327,0.00003500965,0.00001127064,0.0001188582,0.00002514596,0.000009581993,0.00002603434,0.00006849899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1240742,"threshold_uncertainty_score":0.9989534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03822191359303156,"score_gpt":0.3483421313789877,"score_spread":0.3101202177859562,"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."}}