warlock
Datasets
All datasets matching “warlock”oxrl-nips-2026orze-nips-experiments
Orze NIPS 2026 — Experiment Logs
Per-experiment metrics and configs from the NeurIPS 2026 paper "Auto Research Is Not Auto Tuning: Convergence Analysis of 10,000 LLM-Guided Experiments".
This dataset contains the raw experiment logs analyzed in the paper. Two LLM agents (Claude and Gemini) ran 4,233 experiments on the Nexar Dashcam Collision Prediction task, autonomously proposing configurations, running training, and iterating based on results.
Contents… See the full description on the dataset page: https://huggingface.co/datasets/warlockee/orze-nips-experiments.Cherevatenko-fullSidorovichPlahov-fullMelnikov-full