{"id":"W4415974585","doi":"10.1016/j.procs.2025.09.640","title":"Exploring Learner-Action Timing in a Generative AI Supported EFL Ideathon: A KPT Study in Japan","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"Ritsumeikan Global Innovation Research Organization, Ritsumeikan University; Japan Science Society; Ritsumeikan University","keywords":"Usability; Generative grammar; Thematic analysis; Coding (social sciences); Interface (matter); Wilcoxon signed-rank test; Qualitative analysis; User interface","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":[],"consensus_categories":[],"category_scores_codex":[0.001061526,0.0002367796,0.0002718906,0.001415435,0.0002819679,0.0006267338,0.001829385,0.00004161941,0.00000465433],"category_scores_gemma":[0.0001100601,0.0002451035,0.00004133587,0.005733038,0.000113061,0.005048153,0.001106526,0.0005027917,0.00003213103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004536617,"about_ca_system_score_gemma":0.0006173993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003015371,"about_ca_topic_score_gemma":0.0009261973,"domain_scores_codex":[0.9970577,0.0001059711,0.0005278643,0.001157019,0.000545081,0.0006063374],"domain_scores_gemma":[0.9987018,0.0001606229,0.000116807,0.0006519825,0.0002595536,0.0001092392],"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":[0.00005440722,0.002430825,0.3637024,0.0001491929,0.00004092269,0.0002548025,0.1150988,0.04575742,0.01423884,0.01178809,0.0003242699,0.4461599],"study_design_scores_gemma":[0.0005425285,0.0001834857,0.1787212,0.0001492973,0.000003832652,0.00002171004,0.001031665,0.8145226,0.003583921,0.0008301534,0.000127375,0.0002822691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6190394,0.00001292313,0.3774357,0.001332431,0.001372799,0.0004416174,2.248582e-7,0.0001531494,0.0002118359],"genre_scores_gemma":[0.9514912,0.000006881541,0.04718456,0.0008934414,0.00009410469,0.0002691426,5.586314e-7,0.000008086545,0.00005203326],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7687652,"threshold_uncertainty_score":0.9995031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1428689826193871,"score_gpt":0.3632496142660859,"score_spread":0.2203806316466987,"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."}}