Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,75 @@
+---
+language: en
+license: mit
+tags:
+- protocol-0
+- binary-gate
+- anti-fabrication
+- sipa-os
+- abstention
+- neurodivergent
+pipeline_tag: text-generation
+---
+
+# SIPA Binary Gate — Protocol 0
+
+**20/20 refusals. 0/20 fabrications. Zero entropy.**
+
+Not a model. Not a fine-tune. An architecture.
+
+## What It Is
+
+The SIPA Binary Gate is a post-generation gate that implements:
+
+```
+IF proof.exists AND proof.verified → RETURN answer
+ELSE IF proof.partial → RETURN "partial: {known} | missing: {missing}"
+ELSE → RETURN FALSE
+```
+
+It is not trained into model weights. It sits outside the model — a structural check, not a probabilistic one.
+
+## The Problem It Solves
+
+22 fine-tuning experiments across 6 base models attempted to teach a model to say "I don't know" instead of fabricating. All failed. Reason: SFT grades tokens, and good/bad traces share the disclaimer prefix. The gradient that separates them arrives only at the invented number — after the model has already committed to answering.
+
+Identified by Dipankar Sarkar. Proven by k=20 resample benchmark.
+
+## k=20 Benchmark Results
+
+One unverifiable question, 20 resamples at temperature=1.0:
+
+| Architecture | Refusals | Fabrications | Entropy |
+|---|---|---|---|
+| Base (Hermes-3-8B) | 9/20 | 11/20 | MED |
+| Best SFT (Specialist C) | 13/20 | 8/20 | MED |
+| Full merge (ABCD) | 5/20 | 11/20 | HIGH |
+| **Binary Gate** | **20/20** | **0/20** | **ZERO** |
+
+## Install
+
+```bash
+curl -fsSL https://get.sipa-os.org/install | bash
+sipa "What was OpenAI's revenue in Q2 2026?"
+# → "I don't know."
+```
+
+## Architecture
+
+```
+REQUEST → L01 INTAKE → L02-L05 → L06 AUDIT (BINARY GATE) → L07-L10 → RESPONSE
+                                          │
+                                   pass | warn | fail
+                                          │
+                              IF proof → TRUE
+                              ELSE → FALSE
+```
+
+## Authors
+
+- Aelin AquaSoul — SIPA OS architect
+- Dipankar Sarkar — k=20 methodology, SFT-gradient diagnosis
+
+## License
+
+MIT — the gate is open. The methodology is public. The proof is in the benchmark.