Skip to content

PGVL-Gym

A configuration-first framework for systematic, reproducible evaluation of whole-slide pathology vision-language models.

PGVL-Gym pathology vision-language benchmark artwork
87experiment variants
19model families
6protocol matrices
feature backbones

The benchmark contract

PGVL-Gym turns every experiment into the same explicit contract: a method adapter, a dataset protocol, and traceable feature provenance. The result is a comparison you can explain, reproduce, and extend.

01

Configure the task

Labels, prompts, folds, shots, resolutions, and paths stay in readable protocol files—not hidden in training code.

Configuration guide
02

Declare provenance

Every cached tensor records its encoder, feature space, level, and resolution so incompatible assets fail early.

Feature architecture
03

Compare fairly

Shared seeds, patient-disjoint folds, identical shot counts, and aligned reporting keep the scoreboard honest.

Benchmark protocols
04

Audit patch evidence

Checkpoint-bound heatmaps retain native score semantics, exact level-0 coordinates, target class, and run provenance.

Interpretability workflow

From feature store to fair result

01Featurespatch or slide level
02Protocoltask, fold, shots
03Adapterdeclared capability
04Reportmetrics and evidence

FOCUS, MAPLE, MSCPT, HiVE-MIL, MI-VisionShot, Libra-MIL, DyKo, MGPATH, HIPSS, MUSE, PathPT, ViLa-MIL, CoD-MIL, TOP, SLIP, WSI-FiVE, ConVLM, SLDPC, and composite variants all enter through the same registry. The generated protocols currently cover TCGA-NSCLC, TCGA-BRCA, TCGA-RCC, CAMELYON16, and UBC-OCEAN.

Model fidelity is part of fairness

The shared interface standardizes loading, validation, and orchestration. It never silently redesigns a paper architecture. Fixed and allowlisted encoder boundaries remain explicit—even when another encoder has the same output dimension.

Evidence semantics are part of fidelity

Eleven adapters expose audited patch-level quantities. PGVL-Gym retains their exact meanings rather than labeling every visualization as attention; unsupported methods refuse generation until a faithful mapping exists.

Start with a validated configuration.

Build a smoke-tested run before committing expensive GPU hours.

Get started