Field	Value
Method	LIFPO
Base model	`Qwen/Qwen3-4B`
Dataset	`viciousa3gis/hypodiverse`
Pinned dataset revision	`d16867cc49836f72ace9e3667164fa6e4ae76eda`
Evaluation protocol	latent-conditioned generation (8 latent identities)

LIFPO starts from the finite-budget objective that different rollout identities should cover different valid hypotheses. It uses latent rollout identities and inverse-frequency credit while retaining the same exact validity verifier as GRPO.

Exact training and evaluation configurations, per-file model hashes, and the pinned dataset revision are recorded in release_manifest.json and provenance/configs/.

viciousa3gis/hypodiverse-lifpo

HypoDiverse: LIFPO

Provenance

viciousa3gis/
hypodiverse-lifpo