Remove changelog; soften language-coverage limitation

README.md

@@ -113,7 +113,7 @@ ECE ≤ 0.077 on the three strong IndicJevBench datasets — well below the 0.10
 - **English JevBench regression:** the *original* tier drops from 0.681 (mid-training) to 0.569 (final) — a −11pp regression. This is consistent with continued Indic-heavy fine-tuning drifting the decision heads away from English task phrasing. This is expected: Nirṇaya is India-first by design.
 - **Score-type calibration on hard tasks:** ECE on JevBench *hard* tier is 0.388 (catastrophically overconfident on the hardest questions). Practical deployment should apply per-(type, K) temperature scaling on your own calibration split. A calibration recipe will ship alongside the inference package.
 - **Not a generator:** Nirṇaya does not produce free-form text. Use a generative model for open-ended tasks.
-- **Language coverage:** trained on 7 Indic languages (`hi bn ta te kn ml`) + English + Hinglish. Marathi and Gujarati were not available in the training source and are **not** supported in v1.0.
+- **Language coverage:** trained on 7 Indic languages (`hi bn ta te kn ml`) + English + Hinglish. Marathi, Gujarati and other Indic languages will be added in future releases.
 - **Prompt-injection surface:** because Nirṇaya reads `state` as raw text, adversarial content in the state can still influence probabilities. Do not use Nirṇaya as the sole safety gate for adversarial inputs.
 
 ---
@@ -182,9 +182,3 @@ Until the inference package lands, the checkpoint can be loaded via the training
 - **Training frameworks:** [transformers](https://github.com/huggingface/transformers), [PEFT](https://github.com/huggingface/peft), PyTorch
 - **Benchmark inspiration:** TypeSafe AI's Jev / JevBench
 - **Companion benchmark:** [IndicJevBench](https://huggingface.co/datasets/cmul8-hf/IndicJevBench) — released alongside Nirṇaya
-
----
-
-## Changelog
-
-- **v1.0 — 2026-09-25:** Initial public release. Step-18616 checkpoint. Numbers frozen as reported above.