Benchmark auf den gueltigen Stand + UTM-Kennzeichnung

- 'wins all nine' -> 'three of nine ... hold, six ties, none lost'
(Richterversionen waren nicht angeglichen, versionsgleich nachgerichtet 15.09.2026)
- '1/106' -> '1/109.6'
(die 106 kam aus 105.577,9 / 1.000, einer Tausender-Konstante im Zeichenskript)
- die beiden Website-Links tragen jetzt utm_source=huggingface

README.md

@@ -29,10 +29,10 @@ tags:
 [![npm @zensation/algorithms](https://img.shields.io/npm/v/@zensation/algorithms.svg?label=%40zensation%2Falgorithms)](https://www.npmjs.com/package/@zensation/algorithms)
 [![npm @zensation/core](https://img.shields.io/npm/v/@zensation/core.svg?label=%40zensation%2Fcore)](https://www.npmjs.com/package/@zensation/core)
 [![GitHub](https://img.shields.io/badge/GitHub-zensation--ai%2Fzenbrain-black?logo=github)](https://github.com/zensation-ai/zenbrain)
-[![Website](https://img.shields.io/badge/Website-zensation.ai-orange)](https://zensation.ai)
+[![Website](https://img.shields.io/badge/Website-zensation.ai-orange)](https://zensation.ai/?utm_source=huggingface&utm_medium=card&utm_campaign=evergreen)
 [![Live Demo](https://img.shields.io/badge/%F0%9F%A4%97%20Space-Live%20Demo-yellow)](https://huggingface.co/spaces/zensation-ai/zenbrain-playground)
 
-**Head-to-head:** On LongMemEval-500, ZenBrain wins all nine answer-quality comparisons against Letta, Mem0 and A-Mem (3 competitors x 3 LLM judges) under Bonferroni-corrected significance, and reaches 91.3% of a full-context oracle's binary-judge accuracy at 1/106 of the per-query token cost.
+**Head-to-head:** On LongMemEval-500, three of nine answer-quality comparisons hold against Letta, Mem0 and A-Mem — all three against A-Mem, the remaining six are ties, none lost (3 competitors x 3 LLM judges, Bonferroni-corrected, version-matched). ZenBrain reaches 91.3% of a full-context oracle's binary-judge accuracy at 1/109.6 of the per-query token cost.
 
 **Built by:** Alexander Bering — Division Manager in a mid-sized company and Principal Investigator. What is researched here has to survive a Monday morning, not just a review.
 
@@ -125,7 +125,7 @@ const results = await memory.recall('Hebbian learning', { topK: 5 });
 - **Paper (v8, 9 Aug 2026):** https://zenodo.org/records/21858218
 - **PDF:** https://zenodo.org/records/21858218/files/zenbrain-v8.pdf
 - **GitHub:** https://github.com/zensation-ai/zenbrain
-- **Website:** https://zensation.ai/technologie
+- **Website:** https://zensation.ai/technologie?utm_source=huggingface&utm_medium=card&utm_campaign=evergreen
 - **Live demo (HF Space):** https://huggingface.co/spaces/zensation-ai/zenbrain-playground — runs the real open library in your browser
 - **npm packages (7):** [`@zensation/algorithms`](https://www.npmjs.com/package/@zensation/algorithms) · [`@zensation/core`](https://www.npmjs.com/package/@zensation/core) · [`@zensation/adapter-postgres`](https://www.npmjs.com/package/@zensation/adapter-postgres) · [`@zensation/adapter-sqlite`](https://www.npmjs.com/package/@zensation/adapter-sqlite) · [`@zensation/mcp`](https://www.npmjs.com/package/@zensation/mcp) · [`@zensation/ai-sdk`](https://www.npmjs.com/package/@zensation/ai-sdk) · [`@zensation/cli`](https://www.npmjs.com/package/@zensation/cli)
 - **Reproduction packages:** [Mechanism ablation, Tables 7-9](https://doi.org/10.5281/zenodo.22162064) (Apache-2.0) · [Measurement package: judged outputs, flag manifests, analysis scripts](https://doi.org/10.5281/zenodo.22161978) (CC BY 4.0)