docs: mark Jev API doc as stub

README.md

@@ -111,7 +111,7 @@ The existing AUROC results do **not** establish a universal default threshold.
 
 | Deployment | Guide |
 | :--- | :--- |
-| Cloud API | [Single-candidate scoring, best-of-N, batched best-of-N](https://github.com/yiranyyu/MiniCPM-OCR-private/blob/main/docs/minicpm_ocr_jev_api_en.md) |
+| Cloud API | [Single-candidate scoring, best-of-N, batched best-of-N](https://github.com/yiranyyu/MiniCPM-OCR-private/blob/main/docs/minicpm_ocr_jev_api_en.md) (stub — being written) |
 | Docker / local SDK | [Environment, rendering options, service startup](https://github.com/yiranyyu/MiniCPM-OCR-private/blob/main/docs/minicpm_ocr_jev_tutorial_en.md) |
 | vLLM backend | [Service configuration with and without a renderer](https://github.com/yiranyyu/MiniCPM-OCR-private/blob/main/docs/vllm_deploy_jev_en.md) |
 | SGLang | [Deployment guide](https://github.com/yiranyyu/MiniCPM-OCR-private/blob/main/docs/sglang_deploy_jev_en.md) |
@@ -134,7 +134,8 @@ rendering, or forward-pass failures must not be read as low model scores.
 4. Emit selected results in the original reading order and keep pending regions for reviewers.
 
 Use `score` for one candidate, `score_best` for best-of-N within a block, and `score_best_batch`
-across blocks — see the [API documentation](https://github.com/yiranyyu/MiniCPM-OCR-private/blob/main/docs/minicpm_ocr_jev_api_en.md).
+across blocks — see the [API documentation](https://github.com/yiranyyu/MiniCPM-OCR-private/blob/main/docs/minicpm_ocr_jev_api_en.md) (stub for now;
+until it lands use the [vLLM deploy guide for Jev](https://github.com/yiranyyu/MiniCPM-OCR-private/blob/main/docs/vllm_deploy_jev_en.md)).
 
 ### Fine-tuning