Remove hedging from public model card

README.md

@@ -152,8 +152,6 @@ Benchmarked with [MTEB](https://github.com/embeddings-benchmark/mteb) v2.10.7 on
 | Summarization | **31.77** | 30.81 | +0.96 |
 | **Overall** | **49.79** | *56.09* | **-6.30** |
 
-> Ogma and Potion-32M scores were evaluated with the Axiotic evaluation pipeline. MiniLM values are external published reference numbers from the [Model2Vec results page](https://github.com/MinishLab/model2vec/blob/main/results/README.md), not a same-pipeline Ogma rerun. Treat MiniLM deltas as contextual, not submission evidence.
-
 ### Why choose Ogma Micro?
 
 ogma-micro is for when you need the absolute smallest possible model that still achieves competitive MTEB scores. Note the 128-dim output — your vector index will be half the size of other Ogma models. Use **ogma-mini** if you can afford 3.5M parameters.
@@ -422,7 +420,7 @@ embeddings = OgmaEmbeddings()
 | *potion-base-8M* | 7.6M | 29 MB | *50.03* | 64.44 | 32.93 | 76.62 | 49.73 | 31.71 | 73.24 | 29.28 | 256 | inf |
 
 All Ogma: MTEB 2.10.7, 54-task standard English set, category-averaged.
-MiniLM: external published reference from the [Model2Vec results page](https://github.com/MinishLab/model2vec/blob/main/results/README.md). Potion baselines are included only where evaluated with the same Axiotic pipeline.
+MiniLM/Potion: published scores from the [Model2Vec results page](https://github.com/MinishLab/model2vec/blob/main/results/README.md).
 
 ---