Reference

Header and Manifest Schema

Look up syntax, contracts, layouts, algorithms, and exact behavior.

The fixed header is the decoder's first trust boundary. It must contain enough information to locate every section, reject incompatible modes, allocate decode buffers, and validate predictor compatibility before any predictor call is made.

magic: 4 bytes = AIXC
version: u16
flags: u32
unitMode: enum(byte, token)
predictorKind: enum(toy, lzp, byte-model, hf-token)
entropyMode: enum(raw, huffman, zstd)
originalLength: u64
seedOffset, seedLength: u64, u64
decisionOffset, decisionLength: u64, u64
residualOffset, residualLength: u64, u64
metadataOffset, metadataLength: u64, u64
bodyCrc32: optional u32
manifestSha256: optional bytes32

Header fields. A decoder can reconstruct section boundaries and compatibility requirements from the fixed prefix.

\forall s,\; 0 \le offset_s < offset_s + length_s \le |A|

Section bounds. Every referenced section must lie inside the archive byte range.

The manifest is canonical JSON or an equivalent canonical binary map. Required fields include predictor kind, version, tokenizer identity when applicable, tie-break rule, unit mode, residual mode, entropy mode, training corpus identity for sidecar models, and any quantization or runtime switches that affect argmax.

Header and Manifest Schema

Continue exploring