Eight components
Rank-8 truncation per matrix: the dominant structure of the state, with the residual discarded on purpose.
Technology deep-dive
The substrate, in wire format.
What a VIVERE knowledge packet is, how rank-8 compression works, how the six retrieval levels fit together, and — at the bottom of this page — a decoder you can run in your own browser against a real conformance fixture.
01 · Wire format
Packets, pointers, and bytes.
A VIVERE knowledge packet bundles compressed representation records with their metadata into one zlib-framed wire payload. The Python pipeline writes it; the Rust crate reads it; the conformance fixtures pin the two together byte-for-byte.
~150–300 Bper record on the wire
vs ~4 KB for the uncompressed representation
<1 KBVIVERE pointer, tested
asserted byte_size < 1024
734 Bthe demo fixture, whole
three records, zlib-framed
Ratios vary with donor dimensionality; the repository's compression notes carry the dimension-by-dimension breakdown rather than a single headline number.
02 · Compression
Rank 8, reconstructable.
A VIVERE card is a donor model's internal state for one phrase, truncated to eight singular-value components per matrix. A pointer addresses the card in under a kilobyte; the crate reconstructs the state at the far end. The same crate exposes card_pointer_hash, so a pointer's integrity is checkable without the payload.
Pointer, not payload
Fabric exchanges address cards by pointer — sub-kilobyte, hash-checkable — and reconstruct on demand.
Compression has limits
Explained variance falls as donor dimensionality grows; the repo documents where rank 8 stops being enough instead of quoting one flattering ratio.
03 · Retrieval
Six levels, one store.
The Knowledge Fabric is append-only: every record carries provenance, and retrieval descends through six levels, each answering a different question.
| Level | Name | Question it answers | Mechanism |
|---|---|---|---|
L0 | Cache | Have we answered this exact query before? | exact-match lookup |
L1 | Coarse | Which slice of the fabric could answer this? | metadata index filters (domain, type) |
L2 | ANN | What is nearby in embedding space? | approximate nearest-neighbor recall |
L3 | Fine | Of the candidates, what ranks best? | scored rerank of the shortlist |
L4 | Graph | What does this record imply, two hops out? | reasoning-graph traversal |
L5 | VIVERE | What is the compressed original? | VIVERE latent card store |
04 · Teachers & pinning
Every donor pinned, every revision recorded.
Since 2026-09-08, every HuggingFace hub id the code loads must resolve to a pinned 40-hex commit SHA — an AST-sweeping ratchet fails the build on any new unpinned load. A re-published or mutated upstream repo cannot silently change the weights underneath the fabric.
Two teachers, honestly
The consolidated fabric's 1,610-record baseline came from two extraction teachers (Muse-Glimmer-30B and a Qwen model). Larger teachers are registered and pinned targets — not extraction claims.
Pinned, ratchet-tested
Pins live in assets/hf_revisions.json; the ratchet test sweeps the source tree for unpinned from_pretrained calls and fails CI.
Multi-teacher conflict
Where teachers disagree, the foundry resolves by trust-weighted agreement and records the dispute instead of averaging it away.
100%of hub model ids pinned
40-hex revisions, ratchet-tested
1,610records, 2 teachers
consolidated baseline snapshot
05 · Claims boundary
The sentence we are allowed to say.
A sparse recurrent CPU recipient using selected frozen representations extracted from a larger offline donor, with mechanistic routing and causal memory-binding controls.
docs/CLAIMS_BOUNDARY.md — canonical description of the packaged demo; the boundary document governs this site too
06 · Live demo
Decode a packet in your browser.
This demo loads the vivere-cards WebAssembly bundle and decodes a real conformance fixture client-side. Nothing is uploaded; the fixture is 734 bytes of zlib-framed packet generated by the Python golden pipeline to test the wire format — the donor labels inside it are fixture data, not extraction claims.
Bundle not loaded — click above. The wasm bundle is a build artifact; if it is absent, run
make site-build.| Record | Type | Domain | Subject · predicate · object | Confidence | Verification |
|---|
Reference
Glossary
- VIVERE
- Virtual Index of Vector Encoded Representations — the extraction-and-transfer approach: representations taken from a larger donor model, stored compactly, and used by a smaller recipient.
- VIVERE card
- A compressed record of a donor model's internal state for one phrase, truncated to rank 8.
- Packet
- A zlib-framed wire payload bundling compressed records with metadata — the unit the
vivere-cardscrate decodes. - Pointer
- A sub-kilobyte, hash-checkable address for a card; fabric exchanges move pointers, not payloads.
- Knowledge Fabric
- The append-only store behind retrieval: metadata index, ANN, reasoning graph, and the VIVERE latent store across six levels.
- Provenance
- The record of where a fabric entry came from — teacher, method, revision — carried on every record.
- Revision pinning
- Loading every HuggingFace hub id from a pinned 40-hex commit SHA, enforced by a ratchet test.
- RepE vector
- An activation direction encoding a behavior or tone, extracted from a donor model.
- Task vector
- A weight delta capturing procedural knowledge for fine-tuning.
Claims boundary
Reference, not a benchmark sheet.
The numbers on this page are sizes, counts, and policy facts with committed sources — not performance results. No application run has executed, so no efficacy number exists anywhere in this project, including here.