This repository hosts the paper checkpoint matrix for INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models.

The release contains six controlled shared-encoder E5 cells, three training seeds (0, 42, and 3072), and four task-specific shards per seed (PushT, Cube, Reacher, and TwoRoom): 6 x 3 x 4 = 72 checkpoints.

Success rates are percentages averaged over three independently trained seeds. Each checkpoint value averages 100 episodes for evaluation seeds 0, 1, and 42. See PAPER_E5_MATRIX_MANIFEST.json for task-level means, sample standard deviations, checkpoint paths, and SHA-256 hashes. Official LeWM and CLEAR-LeWM results are separate protocols and must not be mixed.

From the accompanying INTACT source release:

The wrapper pins paper-e5-goal-v1, checks the pinned SHA256SUMS record, verifies every downloaded archive, extracts it into STABLEWM_HOME, and then verifies every .pt shard against the checked-in manifest.

For a direct Hub download:

These paper checkpoints use the legacy five-slot Actor checkpoint grammar and must be evaluated with the frozen paper_runtime/ bundled in the source release. The clean training runtime uses the zero-free four-slot Fig. 1 grammar; the Actor parameter shapes are intentionally incompatible. Use the provided paper evaluation wrappers instead of loading these weights through the clean root runtime.

The release is provided under the MIT License. Please cite the INTACT paper; the complete BibTeX entry is maintained in the source repository.