RARE-Mixed

This repository contains the final sample-level Mixed checkpoints from RARE: Reinforcement Learning with Adaptive Rubric Evolution for Open-Ended Generation. Mixed updates may use both unmet quality requirements and observable flaws when multiple saturated criteria are replaced in the same update.

Subfolder	Production style	Final RL step
2d_animation	2D animation	132
3d_stopmotion	3D and stop-motion animation	108
live_action	Live action	94

The held-out scores are 77.09, 75.67, and 71.13 for the three styles, respectively, for an equally weighted average of 74.63. This is a 2.65-point gain over the matched Sample-Static baseline.

Each subfolder is an independent inference-only full checkpoint derived from Qwen/Qwen3-4B-Instruct-2507; optimizer and trainer state are not included. The exact launcher and settings are documented in the RARE repository. Use the corresponding configuration from EurekaTian/RARE for the released system instruction and query format. This card does not add a separate convenience inference command that was not part of the released pipeline. The weights are licensed under Apache-2.0; the dataset is separately licensed under CC BY 4.0. The canonical paper citation will be added after publication metadata is finalized.