A wai.neural.int_hyper bitstream arrived: a factorized side-stream z and the
Gaussian-conditional main stream y, both rANS-coded. This tab decodes it to RGB with the
same pure-i64 Rust that decodes natively, compiled to wasm32 — no onnxruntime-web, no WebGPU,
no float anywhere. The whole path is integer: factorized z → integer
hyper-decoder → integer-σ entropy bucketing → integer synthesis. Because of that (the integer-entropy
contract) the reconstruction is byte-identical on every machine, so the page re-checks its FNV-1a against
the hash the native reference produced — a SOTA-class learned codec verified client-side, no server.
Why this is the moat: the SOTA learned-image family is float, so its entropy decode desyncs on
~1e-5 of cross-platform drift in the scale σ — reproducible only on the same build, never receiptable.
int_hyper is a real pretrained codec (post-training-quantized to integer, ~0.6 dB off
the float baseline) whose entire decode is integer, so the hash above is portable: this browser, a native
sink, and the conformance corpus all produce the same bytes. The wire carried a ~1.4 KB bitstream;
the model is the installed codec. Note: the model files are large (PTQ weights) and not committed —
generate them with tools/wai_sota_int_synth_export.py into demo/int_hyper/.