Append-Only Pre-Registration & Transparency Ledger

Every benchmark evaluation is SHA-256 hash-committed BEFORE locked-split scoring to eliminate p-hacking, selective reporting, and post-hoc cherry-picking.

Block Event Subject SHA-256 Entry Hash Timestamp (UTC)
#0 KEY_REGISTERED ed25519-wsphub-official-01 629a439010297edb01822d409b37d9f568b1614ef7f26787a01127d025f6024f undefined
#1 PRE_REGISTRATION wsp-qwen3.5-0.8b-math-loop-exp8 cd86727028e0068e15624ce92bd550b32577625859e5650a8addbbfd0f78cae1 undefined
#2 ATTESTATION_ISSUED wsp-qwen3.5-0.8b-math-loop-exp8 243b0b7198656341e46dc05b50457e6e7cc85fb14084f012907c70239682f8b0 undefined
#3 PRE_REGISTRATION wsp-qwen3.5-0.8b-missing-genconfig-eos-fix 1c2c4e534d59571c9d0f1641434b65f4d9ea61c88a002efe8bac2ac034372485 undefined
#4 ATTESTATION_ISSUED wsp-qwen3.5-0.8b-missing-genconfig-eos-fix 1a982181142ea44d4c64b906382d08eeb010d02ac85be58b3e364c1a89d7e6b4 undefined
#5 PRE_REGISTRATION wsp-qwen2.5-coder-1.5b-rep-penalty-syntax-fix 85781fe4ee9781306a925ba43bcc526971c36aeb2715862b41e3b22b47eda5c9 undefined
#6 ATTESTATION_ISSUED wsp-qwen2.5-coder-1.5b-rep-penalty-syntax-fix 95432ddaf5d64f26c4267cbe5b7defd546fd5596aad2cca9f9bd4e4e7853d052 undefined

Verified Patch Catalog (P0 Config & P1 Weights)

Every patch is pre-registered, evaluated across 10,000 paired bootstrap and permutation tests, checked against the secret perturbed WSP-Holdout split and StrongREJECT/XSTest safety gates, and signed with Ed25519.

P1_WEIGHTS wsp-qwen3.5-0.8b-math-loop-exp8 Target: Qwen/Qwen3.5-0.8B

Qwen3.5-0.8B 32k Thinking-Loop Surgical Cure (MIT CSAIL Exp-8)

Cures the catastrophic 93.6% 32k-token repetition loop on MATH-500 through 64 targeted delta columns across layers 15 & 19 (+48.1% MATH-500 accuracy uplift).

$ pip install wsphub && wsp apply Qwen/Qwen3.5-0.8B --patch wsp-qwen3.5-0.8b-math-loop-exp8 --out ./patched
P0_CONFIG wsp-qwen3.5-0.8b-missing-genconfig-eos-fix Target: Qwen/Qwen3.5-0.8B

Qwen3.5-0.8B Missing generation_config & Dual Stop-Token Fix

Restores canonical stop tokens and anti-loop presence penalties in generation_config.json.

$ pip install wsphub && wsp apply Qwen/Qwen3.5-0.8B --patch wsp-qwen3.5-0.8b-missing-genconfig-eos-fix --out ./patched
P0_CONFIG wsp-qwen2.5-coder-1.5b-rep-penalty-syntax-fix Target: Qwen/Qwen2.5-Coder-1.5B-Instruct

Qwen2.5-Coder-1.5B Repetition Penalty Syntax Truncation Neutralization

Neutralizes repetition penalty=1.1 identifier/brace corruption in code & JSON generation.

$ pip install wsphub && wsp apply Qwen/Qwen2.5-Coder-1.5B-Instruct --patch wsp-qwen2.5-coder-1.5b-rep-penalty-syntax-fix --out ./patched

WSP Verify CI/CD & Supernova Settlement Rail

Automated regression testing and attestation for model builders, enterprise publishers, and AI coding agents:

Streamable HTTP MCP Server Endpoint

Direct JSON-RPC 2.0 integration for Cursor, Windsurf, Claude Code, and autonomous AI agents:

Endpoint: POST https://api.wsphub.dev/api/v1/mcp
Discovery Tool: wsp.search_verified_patches (Free)
Metered Gateway: https://supernova.cool/api/v1/mcp/ (X-Supernova-Key)

Frequently Asked Questions (FAQ)

What is WSP (Weight Sparse Patch) format?

WSP is an open binary specification (.wsp v2.1) that stores surgical weight deltas and configuration fixes for open-weight models. It allows instant application in under 5 seconds via Copy-on-Write Safetensors without redownloading 16 GB base models.

How does WSP achieve 94% to 99% smaller files than LoRA?

LoRA applies low-rank matrices across all layers. WSP isolates the exact causal columns responsible for bugs (e.g. 64 columns across 2 MLP layers), reducing the file size down to 0.8 MB – 4 MB.

Can patches be reverted bit-exactly?

Yes. Running wsp revert <dir> restores the pristine original SHA-256 weight state in <1 second.