Writing

Journal Paper (* Denotes Equally Contributed)

Yang, Y. (Under Peer Review, 2026). Robust Machine Learning for Regulatory Sequence Modeling under Biological and Technical Distribution Shifts. Preprint available at arXiv: Full Paper: https://doi.org/10.48550/arXiv.2601.14969.

Yang, Y. (Ready for Submission, 2026). From Uncertainty to Failure Attribution: Self-Diagnosing Models for Failure Attribution under Distribution Shift. Preprint available at arXiv: https://doi.org/10.48550/arXiv.2608.07953.

Yang, Y., & Gulbahar, Y. (Under Third-Round Peer Review, 2025). Multimodal Fusion and Interpretability in Human Activity Recognition: A Reproducible Framework for Sensor-Based Modeling. International Journal of Data Science and Analytics (SJR Q1). Preprint available at arXiv: Full Paper: https://doi.org/10.48550/arXiv.2510.22410.

Yang, Y., & Gulbahar, Y. (Published on November 25, 2025). Spatiotemporal Modeling of Water Quality Trends in a Coastal Wildlife Refuge: A Statistical Approach to Ecological Risk and Resource Management. Modeling Earth Systems and Environment (SJR Q1). Full Paper: https://doi.org/10.1007/s40808-025-02691-7. [Easy View (Full Paper)].

Huang, Z.*, Yang, Y.*, & Gulbahar, Y. (Published on December 2, 2025). Understanding the Interconnected Drivers of Mathematics Test Performance: A Longitudinal Study. Studies in Educational Evaluation (SJR Q1). Full Paper: https://doi.org/10.1016/j.stueduc.2025.101539. [Easy View (Full Paper)].

Yang, Y. (Submitted, 2026). Beyond Predictive Uncertainty: Reliable Representation Learning with Structural Constraints. Preprint available at arXiv: Full Paper: https://doi.org/10.48550/arXiv.2601.16174.

Conference Paper (* Denotes the Presenter)

Yang, Y.* (July 2026). A Structure-Aware Deep Learning Architecture for Cognitive Diagnosis and Psychometric Interpretability. Annual International Meeting of the Psychometric Society (IMPS), Seoul, Republic of Korea. https://doi.org/10.48550/arXiv.2607.01278. [My Slides]. [Acceptance Notification].

Yang, Y.*, & Gulbahar, Y. (April 2026). Decoding AI Tutor Effects for Educational Measurement: Temporal, Multi-Outcome, and Behavioral-Cognitive Analysis. Paper presented at the annual meeting of the National Council on Measurement in Education (NCME), Los Angeles, CA, United States. Conference Paper available at NCME Official Website: https://www.xcdsystem.com/proceedings/ncme/8DbqHwv/presentation/27435.cfm?uuid=3EC982ED-A989-8E53-B42BC86334206028. https://doi.org/10.48550/arXiv.2604.16366. [My Slides].

Yang, Y.*, & Gulbahar, Y. (October 2025). Automatic Grading of Student Work Using Simulated Rubric-Based Data and GenAI Models. Conference Paper available at ACL Anthology: https://aclanthology.org/2025.aimecon-wip.5/. [My Slides].

• Paper presented at Artificial Intelligence in Measurement and Education Conference (AIME-Con), National Council on Measurement in Education (NCME) (October 28, 2025), Pittsburgh, PA, United States. [2025 AIME-Con Verification] .

• Paper presented at Columbia University Teachers College (TC) Provost’s Grant Awardee Research Exposition (April 28, 2026), New York, NY, United States. [Columbia TC Presentation Verification]. [Columbia TC Newsletter].

Yang, Y., & Gulbahar, Y.* (March 2026). Exploring the Effects of Various Prompts and LLMs on Coding Automated Constructive Feedback. Poster presented at the Annual Conference of the Society for Information Technology and Teacher Education (SITE), Association for the Advancement of Computing in Education (AACE), Philadelphia, PA, United States. Proceedings available at The Learning and Technology Library: https://www.learntechlib.org/primary/p/2129226/.

Yang, Y.* (Accepted for Presentation and Publication on March 2, 2026). (Presentation Date: June 2026). The Hierarchical Rater Model for Constructed Responses with a Signal Detection Rater (HRM-SDT) Model for Human-AI Grading Comparisons in Rubric-Based Coding Assessment. Accepted by the Modern Modeling Methods Conference, New York, NY, United States. [Acceptance Notification].

Yang, Y.* & Gulbahar, Y. (Presented and Published on May 8, 2026). Investigating Students’ Cognitive Skill Profiles in Computational Thinking: A Q-Matrix Validation Approach Using Bebras Interactive Task Data and Cognitive Diagnostic Models. Annual Psychology at Columbia University TC Student Research Conference, New York, NY, United States. https://doi.org/10.5281/zenodo.20102194.