Peer-reviewedCC BY 4.0Scientific Reports
Diagnostic probes reveal shortcuts induced by the benchmark protocol in vision-language model annotation pipelines for video-based self-harm detection
Related
- An accuracy and calibration benchmark of scGPT pipelines and matched classical models for cell type annotation
- MillionTrees: A global benchmark for tree detection across geography, sensor, and annotation geometry
- scBOA: Bayesian optimization of single-cell analysis pipelines for robust annotation and discovery
- Where single-cell foundation models help: a benchmark of annotation, perturbation and regulatory inference against simple baselines
- An annotation-overlap-flagged rare-disease gene-prioritisation benchmark and PMC index recipe
BibTeX
@article{lee2026diagnostic,
title = {{Diagnostic probes reveal shortcuts induced by the benchmark protocol in vision-language model annotation pipelines for video-based self-harm detection}},
author = {Yourack Lee and Hyun-Ghang Jeong and Hyun-Soo Choi},
journal = {Scientific Reports},
year = {2026},
month = nov,
doi = {10.1038/s41598-026-78750-5},
url = {https://www.nature.com/articles/s41598-026-78750-5},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Diagnostic probes reveal shortcuts induced by the benchmark protocol in vision-language model annotation pipelines for video-based self-harm detection
AU - Yourack Lee
AU - Hyun-Ghang Jeong
AU - Hyun-Soo Choi
PY - 2026
DA - 2026/11/09
JO - Scientific Reports
DO - 10.1038/s41598-026-78750-5
UR - https://www.nature.com/articles/s41598-026-78750-5
SN - 2045-2322
ER -