Code
Open-source code released alongside our publications for full reproducibility.
We release the code behind our studies so that results can be inspected and reproduced. Each entry links to a public repository and the paper it accompanies.
Synthetic-Panel Audit
Apache-2.0 · CC BY 4.0Audit protocol and benchmark for "Everyone's taste and no one's: an audit protocol for LLM synthetic panels in UX research." Each of 18,448 LabintheWild participants is paired with a persona-conditioned digital twin that rates the same websites, yielding about 620,000 synthetic ratings across five model families, audited against a noise ceiling from human re-ratings. The package ships the audit code, the full synthetic-rating data, a demographic-oracle bound, and a screening rule that identifies in advance the populations for which a synthetic panel should be refused.
The LabintheWild human anchor (CC BY-NC-SA 3.0, Reinecke & Gajos, CHI 2014) is not redistributed; a download script fetches it from the original authors' site.
View on GitHub Zenodo archiveACES — Adaptive Conformal Early-warning System
MIT LicenseReproduction code for "Calibration, not loss design, governs prediction-interval quality: an adaptive conformal early-warning system for algal-bloom forecasting." The benchmark crosses five heteroscedastic loss families with three forecasting backbones (Mamba, GRU, inverted Transformer), pairs every predictor with raw, split-conformal, and online adaptive-conformal calibration, and evaluates an early-warning decision layer on the calibrated intervals. The central finding: the calibration layer — not the training loss — governs prediction-interval quality under distribution shift.
Uses publicly available observations from the Korean national water-quality monitoring network (water.nier.go.kr), Geum River basin, 2021–2024. Raw records are not redistributed; see the repository README for the preprocessing pipeline.
View on GitHubSupported by IITP (RS-2026-25522834, Physics-AI Hybrid Disaster Response Technology), NRF (RS-2026-25493931), and the Hankuk University of Foreign Studies Research Fund of 2026.