| title: WAVEBench | |
| emoji: 🧬 | |
| colorFrom: blue | |
| colorTo: green | |
| sdk: static | |
| pinned: false | |
| # WAVEBench | |
| WAVEBench is a benchmark for evaluating evolutionary generalization in genome language models through viral-versus-cellular classification of wastewater metagenomic reads. It combines taxonomic cross-validation, fixed evaluation reads, and composition controls to measure performance across levels of taxonomic novelty. | |
| ## Resources | |
| - [Benchmark data](https://huggingface.co/datasets/WAVEBench/wavebench): Kraken2 reports, taxonomic splits, read manifests, taxonomy, and frozen evaluation reads at three tiers. | |
| - [Figures and results](https://huggingface.co/datasets/WAVEBench/wavebench-figures): saved evaluation outputs, figure-generation inputs, and current manuscript and regenerated figures. The dataset card documents missing historical inputs and reproduction limits. | |
| The datasets are currently private and available to authorized collaborators. Full raw and deduplicated corpora and original per-read Kraken2 outputs are not distributed. Data provenance and preprocessing methods will be described in the accompanying paper (link forthcoming). | |