17.6 MB
68 files
Updated about 2 months ago
Name
Size
datasets
docs
engine
examples
model
server
.gitattributes168 Bytes
xet
.gitignore36 Bytes
xet
Dockerfile1.09 kB
xet
LICENSE1.17 kB
xet
PUSHING.md824 Bytes
xet
README.md5.54 kB
xet
inference.py3.84 kB
xet
README.md

SyFox Giant — a broad System-One decision engine (SI substrate, no NN)

One giant SyFox fabric family covering 16 decision domains (customer support, banking intents, spam, emotions, moderation, news topics, product sentiment, entity typing, boolean comprehension, game commands, guardrails) plus per-script substrates for Bengali / Devanagari / Cyrillic with automatic script routing. No transformer, no neural network, no pattern matching: every decision comes from a C++ SI substrate — energy injection → dissipative settle → resonance readout → honest silence. The lanes ARE the knowledge; every one is inspectable in model/*/substrate.bin.

Built from 76,142 real/synthetic-verified training rows across 16 domains, trained with the three failure-mode fixes learned from the model-xl RCA: empty per-row instructions, globally-unique opaque anchors (278), and round-robin domain interleaving. Full measured evaluation: docs/EVALUATION.md.

Headline measured numbers (hidden splits, scored once)

domain class acc router end-to-end
tickets_en 0.904 0.831 0.761
sms spam 0.752 0.233 0.222
enron email spam 0.752 0.394 0.323
hate/offensive 0.653 0.381 0.277
ag_news topics 0.604 0.320 0.206
amazon polarity 0.571 0.339 0.189
dbpedia entities 0.475 0.403 0.204
boolq (boolean) 0.531 0.097 0.059
bank77 (77-way) 0.023 0.931 0.022
tickets_bn (bengali substrate) 0.943 1.000 0.943
tickets_hi (devanagari substrate) 0.920 1.000 0.920
tickets_ru (cyrillic substrate) 0.959 1.000 0.959

Honest notes: the single 16-way router is the end-to-end bottleneck for same-script domains — blind routing alone measures 0.400 on hidden (23,528 rows) and the table's router column is the informed condition (router + the true domain's class question asked together); naming the domain in the API gives the class numbers. bank77's 77-way readout collapses in a shared fabric (dedicated-fabric reference: 0.081); boolq stays near majority — boolean passage comprehension is a measured limit of bag-of-words SI physics. Latency ≈ 6-11 ms/row on the 43k-node latin fabric.

Files

engine/      C++ SI substrate core (core/*.hpp, src/*.cpp) — builds with make
server/      FastAPI HTTP bridge (v3 API, CLI-equal flags)
inference.py thin python wrapper (auto script routing)
model/       giant-{latin,bengali,devanagari,cyrillic}/substrate.bin (+meta, calibration)
datasets/    eval hidden splits, probes, schemas, MANIFEST (SHA-256), DATASETS.md
docs/        EVALUATION.md, ARCHITECTURE.md, PROBING.md, ZEROSHOT.md
examples/    JSON payloads + curl + python usage
Dockerfile   HuggingFace Spaces (builds engine, serves on 7860)

Usage (python)

from inference import SyFox
m = SyFox()                       # loads model/giant-<script> per detected script
r = m.decide("I was charged twice on my last invoice, please refund.")
print(r["answers"]["domain"])     # router: choice + probabilities + confidence

# ask a named domain's question directly (skips the router bottleneck):
r = m.decide("I was charged twice on my last invoice, please refund.",
             domain="bank77")
print(r["answers"]["intent"])     # 77-way choice with probabilities

Usage (HTTP, what the Space runs)

curl -X POST http://localhost:7860/v1/systemone -H 'Content-Type: application/json' -d '{
  "state": "Congratulations! You won a £1000 prize. Call now to claim!",
  "questions": {"domain": {"type": "choice", "instructions": "",
    "criteria": {"rt00": "support billing sales technical", "rt05": "text messages spam",
                  "...": "see datasets/schemas.json"}}},
  "options": {"energy_norm": true, "defer_margin": 0.05}
}'

The server also exposes /v1/health, /v1/models, /v1/deferrals (active-learning mirror) and per-call options energy_norm, salience_gating, miller_window, ngrams, defer_margin, evidence.

Docker (HuggingFace Spaces)

The included Dockerfile builds the engine from source and serves the v3 API on port 7860.

Training recipe (reproduce or extend)

See docs/EVALUATION.md §Reproduce. Corpus + tooling live in the main SyFox repo (tools/hf_fetch.py, tools/giant_prepare.py, tools/giant_bench.py, tools/router_sweep.py). Constraint discipline: hidden splits are firewall-enforced (never taught, never calibrated on); all model/wording selection happened on cal; the core physics was never modified.

Limitations

  • Single-router e2e is bottlenecked by 16-way choice in one fabric (measured; wording sweep shows it is the readout mechanism, not the wording).
  • 77-way banking intents need a dedicated fabric (or arbitration) at this scale.
  • Boolean passage comprehension is near-majority — the substrate reads lexical fields, not logic.
  • Zero-shot composition (constraints, topology) is NOT solved by scale — see docs/ZEROSHOT.md for the measured two-dimension separation.

License & credit

MIT © 2026 Mr-DS-ML-85. Core mechanics ported from the author's Synthetic-Intelligence research substrate. Dataset licenses: see datasets/DATASETS.md.

Total size
17.6 MB
Files
68
Last updated
Sep 27
Pre-warmed CDN
US EU US EU

Contributors