from lightningrod-python-sdk47
Worked examples and pipelines for generating forward-looking (GRPO) binary forecasting datasets: seeds → question generation → labeling → lint → split → train.
Provides production-ready example pipelines for generating forward-looking binary forecasting datasets (GRPO). The skill documents end-to-end patterns: seed generation (news, GDELT, or filesets), question generation with ForwardLookingQuestionGenerator, context generation, automated labeling, linting, temporal splitting, and training configuration recommendations for fine-tuning models. Multiple domain examples (sports, politics, military, general forecasting, timestamped documents) illustrate practical parameters and notebooks to reproduce results.
Use when building forecasting datasets or experimenting with GRPO-style fine-tuning. Useful for teams preparing high-quality labeled forecasting data, testing question pipelines on small seeds, or scaling to production datasets (thousands of seeds). Not intended for casual Q&A — it's for dataset engineers and modelers.
Python SDK consumers and engineers using LightningRod tooling; compatible with agents that can run Python SDK calls, notebook-driven workflows, and training orchestrations (local Python agents, Jupyter/Colab, and CI-driven training pipelines).
This skill has not been reviewed by our automated audit pipeline yet.
