ConnectomeBench2: A Unified Benchmark for Automated Connectomic Proofreading

Proofreading—correcting segmentation errors in 3D brain reconstructions—is the rate-limiting step in synapse-resolution connectomics. We release ConnectomeBench2, a unified multi-species dataset of over 302,401 expert-labeled proofreading decisions with >2,000,000 associated images spanning four major open connectomes (mouse, human, zebrafish, fly), spanning both split and merge error correction. Trained on this dataset, a single Vision Transformer with shared encoders for mesh geometry and electron microscopy reaches human-level accuracy across species for split error correction and merge error identification; with performance scaling with data size and improving with species diversity. Beyond accuracy, we show that the model is well-calibrated within distribution, that measures of distribution distance predict where calibration and accuracy will degrade on unseen data, and that connectomics-specific pretraining and active learning-based sample selection show potential to substantially reduce the labeling effort needed to extend to new species and brain regions. The benchmark provides the infrastructure to train and evaluate increasingly capable vision models for connectomic proofreading.