Maqola

Independent Engineering Transfer After Traceable Generative-AI-Assisted Learning: A Six-University Controlled Trial with Deterministic Cluster Allocation in Agricultural Engineering Education

Сыромятников Ю.Н.Institute of Soil and Plant Sciences, Latvia University of Life Sciences and Technologies, LV-3001 Jelgava, LatviaFarmon МамаtovDepartment of Agricultural Engineering, Faculty of Irrigation Engineering, Karshi State Technical University, Karshi 180100, UzbekistanKhurshid ChuyanovDepartment of Higher Mathematics, Faculty of Energy Engineering, Karshi State Technical University, Karshi 180100, UzbekistanZafar BatirovDepartment of Pedagogy and Teaching Methodology, Faculty of Pedagogy, University of Economics and Pedagogy (Non-State Educational Institution), 11A Jayxun Street, Gungon MFY, Karshi 180100, UzbekistanDustmurod ChuyanovDepartment of Transport and Civil Engineering, Faculty of Transport and Civil Engineering, Karshi State Technical University, Karshi 180100, UzbekistanMakhmatmurod ShomirzaevDepartment of Technological Education, Termez State University, Termez 190111, UzbekistanДилрабо ШадиеваDepartment of Russian Linguistics, Termez State University, Termez 190111, UzbekistanKhurshid IlkhomovBukhara State Medical Institute named after Abu Ali ibn SinoGulandom Jo’rayevaDepartment of Pedagogy and Teaching Methodology, Faculty of Pedagogy, University of Economics and Pedagogy (Non-State Educational Institution), 11A Jayxun Street, Gungon MFY, Karshi 180100, UzbekistanMirshohid EgamovDepartment of Higher Mathematics, Faculty of Energy Engineering, Karshi State Technical University, Karshi 180100, Uzbekistan

2026en

ABI

Annotatsiya

Generative artificial intelligence (GenAI) can support engineering problem solving, but whether AI-assisted practice transfers to independent performance after the tool is removed remains unclear. This multicentre controlled trial evaluated a traceable five-stage GenAI-assisted learning configuration in agricultural engineering education. Twenty-eight second- and third-year classes from six universities in Uzbekistan were assigned within nine teacher blocks by deterministic constrained minimization to GenAI (14 classes) or structured active-control (14 classes) groups. Both groups completed the same 16-week module, tasks, software, contact time, feedback, and verification requirements. They differed in the source and adaptivity of a provisional alternative used after an independent attempt: bounded adaptive GenAI dialogue versus a version-controlled curated alternative. The full assigned cohort included 656 students; likelihood-based available-outcome analyses included 641 immediate and 589 delayed outcomes. Kenward–Roger analyses estimated an adjusted immediate difference of 2.78 points (95% confidence interval (CI) [2.02, 3.55]; p < 0.001; model-based d = 0.72) and a delayed difference of 2.34 points (95% CI [1.54, 3.14]; p < 0.001; d = 0.51). The results show a positive adjusted association for the evaluated traceable instructional configuration, but deterministic post-baseline allocation limits causal interpretation.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.3390/app16188949

Iqtiboslar va manbalar

0 ta iqtibos22 ta foydalanilgan manba