1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0) that answers typed decision questions for a personal agent with long-term memory, with calibrated probabilities. Code, pre-registration, results and technical report: - Unpacked from the frozen training output qwen-adapter.tar.gz, SHA-256 6b07a7d36eba59b9cfd9cf440bdc5783f4fc12d4d726cfa5beef2462860d8d81 (per-file hashes in release-manifest.json). - Frozen as the final candidate after two hill-climbing rounds; passed the one-shot pre-registered HIDDEN gate; then compared once with five other models on a public TEST set. LoopPolicy is the Hugging Face release name of the PersonaLoop research artifacts: a calibrated personal-agent policy built through…