{"id":"W4413611910","doi":"10.1016/j.rmal.2025.100248","title":"Generating synthetic data for CALL research with GenAI: A proof-of-concept study","year":2025,"lang":"en","type":"article","venue":"Research Methods in Applied Linguistics","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Proof of concept; Computer science; Data science","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":["metaresearch"],"category_scores_codex":[0.03811517,0.0001530173,0.0004459471,0.001025963,0.000428351,0.0003077405,0.00292869,0.0001042563,0.000003123345],"category_scores_gemma":[0.03153372,0.0001265904,0.00003276775,0.003718342,0.0002849143,0.0000386954,0.001990587,0.0007686893,7.578697e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000139081,"about_ca_system_score_gemma":0.0009133724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001617295,"about_ca_topic_score_gemma":0.0001768917,"domain_scores_codex":[0.9935895,0.002677077,0.0006825424,0.001100255,0.001209662,0.0007409677],"domain_scores_gemma":[0.9867215,0.007853655,0.0001165169,0.002977309,0.002219186,0.0001118822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001435119,0.001360912,0.0007326862,0.0004917813,0.0002110312,0.00002521038,0.003042732,0.009546084,0.002585373,0.4828088,0.001732655,0.4973192],"study_design_scores_gemma":[0.0006361407,0.0002988461,0.0000319479,0.0001193705,0.00002324203,2.665103e-7,0.0007445671,0.9589091,0.01083266,0.02021732,0.008030911,0.0001556431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002646856,0.0002317166,0.9892524,0.0001009893,0.0001226633,0.001857832,0.00001178305,0.00002658661,0.008131338],"genre_scores_gemma":[0.2618015,0.000006666502,0.7375081,0.00001467688,0.0001520129,0.0002572812,0.000016518,0.00001472739,0.0002284788],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.949363,"threshold_uncertainty_score":0.9904628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3565748183624333,"score_gpt":0.5723938787290209,"score_spread":0.2158190603665877,"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."}}