Pre-registration (frozen 8 Nov 2026): replication of the TRIBE test-time-adaptation advantage on CIFAR10-C under GLI-TTA-F (arXiv 2309.14949), as published and with every method's learning rate tuned equally

Frozen protocol, decision code, job design, harness, planted-effect table and kernel for a private pre-registered replication, deposited before any confirmatory run. Clause: TRIBE's relative error reduction over the strongest compared baseline (published 36.0% at imbalance factor 100) over five stream seeds, in an as-published arm and an equal-learning-rate-tuning arm. Verdicts are Replicated / Did not replicate / Inconclusive under protocol X.