Org card: symbolic-morphology independently reproduced

README.md

@@ -45,7 +45,7 @@ Alternative attention · SUBLEQ · integer computing · formal proofs · the har
 | [hilbert-4b-baseline-GGUF](https://huggingface.co/Snapkitty/hilbert-4b-baseline-GGUF) | Hilbert's 4B baseline decision model as Q8_0 / Q4_K_M GGUF. **Q8_0 matches BF16 on 99.3% of decisions**, with [row-level evidence](https://github.com/SNAPKITTYAGENT9NOVA/SemIf-OpenJev/tree/master/results/gguf) |
 | [toolgate-bench](https://huggingface.co/datasets/Snapkitty/toolgate-bench) | Benchmark for tool-call gating in LLM agents (accept / require approval / reject), with a frozen held-out split |
 | [snapkitty-nemotron-harness v0.3.0](https://huggingface.co/Snapkitty/snapkitty-nemotron-harness) | Fail-closed tool gate for local agents: **0% unsafe passes** on ToolGate-Bench v1, ~24 µs per decision |
-| [symbolic-morphology](https://huggingface.co/Snapkitty/symbolic-morphology) | Learns Latin verb morphology from raw letters with hand-derived gradients and **no ML framework**, in six implementations benchmarked across 9 runtimes, down to NAND gates |
+| [symbolic-morphology](https://huggingface.co/Snapkitty/symbolic-morphology) | Learns Latin verb morphology from raw letters with hand-derived gradients and **no ML framework**, in six implementations benchmarked across 9 runtimes, down to NAND gates. **Accuracy and loss independently reproduced** ([details](https://huggingface.co/Snapkitty/symbolic-morphology/blob/main/VERIFICATION.md)) |
 
 ---
 

hub.html

@@ -105,7 +105,7 @@
         <div class="card-foot"><div class="tags"><span class="tag">typescript</span><span class="tag">guardrails</span></div><div class="links"><a class="link" href="https://huggingface.co/Snapkitty/snapkitty-nemotron-harness">Hugging Face</a></div></div></article>
       <article class="card"><div class="card-top"><span class="badge new">New</span><span class="badge kind">model</span><span class="badge lic">AGPL-3.0</span></div>
         <h3><a href="https://huggingface.co/Snapkitty/symbolic-morphology">symbolic-morphology</a></h3>
-        <p>Learns Latin verb morphology from raw letters with hand-derived gradients and no ML framework, benchmarked across 9 runtimes down to NAND gates.</p>
+        <p>Learns Latin verb morphology from raw letters with hand-derived gradients and no ML framework, benchmarked across 9 runtimes down to NAND gates. Accuracy and loss independently reproduced.</p>
         <div class="card-foot"><div class="tags"><span class="tag">rust</span><span class="tag">nand</span></div><div class="links"><a class="link" href="https://huggingface.co/Snapkitty/symbolic-morphology">Hugging Face</a><a class="link" href="https://github.com/SNAPKITTYWEST/symbolic-morphology">GitHub</a></div></div></article>
     </div>
   </section>