SPRIIA study of persistent information
Use

Swimmer

Does the update belong to this system?

Swap own-system and wrong-system persistent updates while the predictor stays fixed, then measure how the response changes.

Fixed predictorrecipient-specific update tests
Motion preview
Physics demonstration · joint drive and reversalProject-generated demonstration · MuJoCo simulation. Source & changes
Across independent experiences

What persists.

The recipient system.

Across distinct realizations

What changes.

Own-system versus wrong-system persistent update.

Experience → prediction

The task.

Persistent update + current query/action.

→ State response through fixed predictor weights.

Evaluated instance

The comparison.

Frozen JEPA / GRU bases · update substitution.

Controls. Own-system, wrong-system and matched update conditions.

Interpreting the evidence

What stays fixed in the test.

Base predictor weights and the recipient system are fixed. Each architecture retains its own training-only normalization.

What this setting establishes.

The study isolates recipient-specific persistent-update use across frozen bases.

Scope of the evidence

This is not additional Align/Cross source training. Effects are interpreted within architecture; the custom three-link system is not interchangeable with official Swimmer-v5.

Full result record

Measurements and comparisons.

Reported results are kept with their own populations and conditions. Development, held-out and sealed comparisons remain separate.

01 / Study Table 26

Recipient-specific updates through frozen predictors

512 prospective systems disjoint from training/selection; 3 adapter checkpoints

Wrong-system minus own-system error, ×10⁻⁵ ↑

Recipient-specific updates through frozen predictors
Frozen baseGain ×10⁻⁵95% interval ×10⁻⁵Systems with positive gain
Persistent-JEPA5.329[3.930,6.724]65.04%
Masked-GRU (64101)6.930[5.415,8.621]67.97%
Masked-GRU (64103)6.661[4.878,8.486]68.36%

Bold marks each frozen base’s own recipient-specific update gain.

  • Persistent-JEPAEach base retains its own architecture and training normalization. Gain magnitudes are not a cross-architecture ranking.

Gain is wrong-system minus own-system update error through identical frozen weights, in 10⁻⁵ units. Intervals use 4,000 paired-system bootstrap draws on 512 new systems. The three bases have different architectures and normalizations, so gain magnitudes are not directly ranked.