# Claims and Scope

Generated from [claims.json](https://horizonrunmap.com/claims.json). How can storage precision, execution precision, residency and data movement be coordinated under a constrained GPU-memory budget?

## Implemented and measured claims

- Selective INT4 compression of routed experts with a separate FP16 non-routed path. Status: implemented-in-recorded-paths. [Source](https://horizonrunmap.com/architecture.md)
- Compact expert GPU execution with FP16 activations and recorded scalar/grouped executors. Status: implemented-in-recorded-paths. [Source](https://horizonrunmap.com/evidence.md)
- Partial residency observations under the selected campaign contract. Status: measured. Experiment: residency39.
- OLMoE c64 full residency observations with Grouped T3. Status: measured. Experiment: residency39.
- Complete IFEval instruction-following evaluation of retained Horizon responses. Status: measured. Experiment: ifeval541.

## Not claimed

- fastest MoE runtime.
- SOTA throughput.
- runtime-to-runtime superiority.
- superiority over llama.cpp.
- general BF16 quality equivalence.
- validated frontier-scale deployment.
- independently reproduced runtime generation.
- world-first quantization, offloading or caching.

## Experimental interpretation

- OLMoE c30-c60 use PRODUCT-core scalar; c64 uses Grouped T3. This is not a residency-only comparison.
- IFEval 541 and the earlier 120-pair behavioral study are separate experiments.
- Published artifacts enable their declared verification, not full independent runtime reproduction.
- A shared architectural explanation does not certify every executor against every ADR 0009 invariant.

Runtime source access: private by author decision. Public evidence verification does not rerun the private runtime. [Evidence and verification](https://horizonrunmap.com/en/research/evidence) identifies each admitted experiment and its source artifacts.