@misc{vanderbilt_goldmark_2026,
	title = {{GOLDMARK}: {Governed} {Outcome}-{Linked} {Diagnostic} {Model} {Assessment} {Reference} {Kit}},
	copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International},
	shorttitle = {{GOLDMARK}},
	url = {https://arxiv.org/abs/2603.20848},
	doi = {10.48550/ARXIV.2603.20848},
	abstract = {Computational biomarkers (CBs) are histopathology-derived patterns extracted from hematoxylin-eosin (H\&E) whole-slide images (WSIs) using artificial intelligence (AI) to predict therapeutic response or prognosis. Recently, slide-level multiple-instance learning (MIL) with pathology foundation models (PFMs) has become the standard baseline for CB development. While these methods have improved predictive performance, computational pathology lacks standardized intermediate data formats, provenance tracking, checkpointing conventions, and reproducible evaluation metrics required for clinical-grade deployment.
 We introduce GOLDMARK (https://artificialintelligencepathology.org), a standardized benchmarking framework built on a curated TCGA cohort with clinically actionable OncoKB level 1-3 biomarker labels. GOLDMARK releases structured intermediate representations, including tile coordinate maps, per-slide feature embeddings from canonical PFMs, quality-control metadata, predefined patient-level splits, trained slide-level models, and evaluation outputs. Models are trained on TCGA and evaluated on an independent MSKCC cohort with reciprocal testing.
 Across 33 tumor-biomarker tasks, mean AUROC was 0.689 (TCGA) and 0.630 (MSKCC). Restricting to the eight highest-performing tasks yielded mean AUROCs of 0.831 and 0.801, respectively. These tasks correspond to established morphologic-genomic associations (e.g., LGG IDH1, COAD MSI/BRAF, THCA BRAF/NRAS, BLCA FGFR3, UCEC PTEN) and showed the most stable cross-site performance. Differences between canonical encoders were modest relative to task-specific variability.
 GOLDMARK establishes a shared experimental substrate for computational pathology, enabling reproducible benchmarking and direct comparison of methods across datasets and models.},
	urldate = {2026-04-03},
	publisher = {arXiv},
	author = {Vanderbilt, Chad and Campanella, Gabriele and Singi, Siddharth and Nanda, Swaraj and Chen, Jie-Fu and Kamali, Ali and Boroujeni, Amir Momeni and Kim, David and Yakoub, Mohamed and Benhamida, Jamal and Hameed, Meera and Kumar, Neeraj and Goldgof, Gregory},
	year = {2026},
	note = {Version Number: 1},
	keywords = {Computational Engineering, Finance, and Science (cs.CE), Computer Vision and Pattern Recognition (cs.CV), FOS: Biological sciences, FOS: Computer and information sciences, Tissues and Organs (q-bio.TO)},
}

@misc{GOLDMARKwebsite2026,
  author       = {Vanderbilt, Chad and Campanella, Gabriele and Singi, Siddharth and Nanda, Swaraj and Chen, Jie-Fu and Kamali, Ali and Boroujeni, Amir Momeni and Kim, David and Yakoub, Mohamed and Benhamida, Jamal and Hameed, Meera and Kumar, Neeraj and Goldgof, Gregory},
  title        = {GOLDMARK: Governed Outcome-Linked Diagnostic Model Assessment Reference Kit},
  year         = {2026},
  howpublished = {\url{https://artificialintelligencepathology.org}},
  note         = {Accessed April 3, 2026}
}