datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
smartgridbench-review-artifact
SmartGridBench Review Artifact
This anonymous reviewer artifact contains the paper-facing SmartGridBench scenario and evidence tables for a NeurIPS 2026 Evaluations & Datasets submission.
SmartGridBench evaluates tool-using language agents on Smart Grid transformer-maintenance workflows. The package includes 36 canonical scenario definitions (31 hand-authored plus 5 promoted generated scenarios), 5 negative schema fixtures, paper-grade evidence registries, summary tables, a compact… See the full description on the dataset page: https://huggingface.co/datasets/garn-garn/smartgridbench-review-artifact.smartgridbench-review-artifact
SmartGridBench Review Artifact
This anonymous reviewer artifact contains the paper-facing SmartGridBench scenario and evidence tables for a NeurIPS 2026 Evaluations & Datasets submission.
SmartGridBench evaluates tool-using language agents on Smart Grid transformer-maintenance workflows. The package includes 31 hand-authored scenario definitions, 5 negative schema fixtures, paper-grade evidence registries, summary tables, a compact judge-score table, and a small manual judge audit… See the full description on the dataset page: https://huggingface.co/datasets/paideiamaster/smartgridbench-review-artifact.smart_grid_renewable_energy_telemetryiot_smart_grid_load_telemetry