glmocr 0.1.1__tar.gz

glmocr-0.1.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Zhipu AI
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

glmocr-0.1.1/PKG-INFO

@@ -0,0 +1,423 @@
+Metadata-Version: 2.4
+Name: glmocr
+Version: 0.1.1
+Summary: GLM OCR - Optical Character Recognition powered by GLM
+Home-page: https://github.com/ZHIPUAI/glm-ocr
+Author: ZHIPUAI
+Author-email: zai-org <wenmeng.yu@aminer.cn>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/zai-org/glm-ocr
+Project-URL: Repository, https://github.com/zai-org/glm-ocr
+Project-URL: Documentation, https://github.com/zai-org/glm-ocr#readme
+Project-URL: Issues, https://github.com/zai-org/glm-ocr/issues
+Keywords: ocr,glm,ai,vision
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pillow>=12.1.0
+Requires-Dist: requests>=2.32.0
+Requires-Dist: pydantic>=2.12.0
+Requires-Dist: wordfreq>=3.1.0
+Requires-Dist: PyYAML>=6.0.0
+Requires-Dist: portalocker>=3.2.0
+Requires-Dist: python-dotenv>=1.2.0
+Requires-Dist: torch>=2.10.0
+Requires-Dist: torchvision>=0.25.0
+Requires-Dist: transformers>=5.3.0
+Requires-Dist: sentencepiece>=0.2.0
+Requires-Dist: accelerate>=1.13.0
+Requires-Dist: opencv-python>=4.13.0
+Requires-Dist: pypdfium2>=5.6.0
+Requires-Dist: flask>=3.1.0
+Provides-Extra: layout
+Requires-Dist: torch>=2.10.0; extra == "layout"
+Requires-Dist: torchvision>=0.25.0; extra == "layout"
+Requires-Dist: transformers>=5.3.0; extra == "layout"
+Requires-Dist: sentencepiece>=0.2.0; extra == "layout"
+Requires-Dist: accelerate>=1.13.0; extra == "layout"
+Requires-Dist: opencv-python>=4.13.0; extra == "layout"
+Provides-Extra: pdf
+Requires-Dist: pypdfium2>=5.6.0; extra == "pdf"
+Provides-Extra: server
+Requires-Dist: flask>=3.1.0; extra == "server"
+Provides-Extra: all
+Requires-Dist: torch>=2.10.0; extra == "all"
+Requires-Dist: torchvision>=0.25.0; extra == "all"
+Requires-Dist: transformers>=5.3.0; extra == "all"
+Requires-Dist: sentencepiece>=0.2.0; extra == "all"
+Requires-Dist: accelerate>=1.13.0; extra == "all"
+Requires-Dist: opencv-python>=4.13.0; extra == "all"
+Requires-Dist: pdf2image>=1.16.0; extra == "all"
+Requires-Dist: flask>=3.1.0; extra == "all"
+Provides-Extra: dev
+Requires-Dist: pytest>=9.0.0; extra == "dev"
+Requires-Dist: black>=26.3.0; extra == "dev"
+Requires-Dist: flake8>=7.0.0; extra == "dev"
+Requires-Dist: mypy>=1.19.0; extra == "dev"
+Requires-Dist: pre-commit>=4.5.0; extra == "dev"
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+
+## GLM-OCR
+
+<div align="center">
+<img src=resources/logo.svg width="40%"/>
+</div>
+<p align="center">
+    👋 Join our <a href="resources/WECHAT.md" target="_blank">WeChat</a> and <a href="https://discord.gg/QR7SARHRxK" target="_blank">Discord</a> community
+    <br>
+    📍 Use GLM-OCR's <a href="https://docs.z.ai/guides/vlm/glm-ocr" target="_blank">API</a>
+</p>
+
+<div align="center">
+  <a href="README_zh.md">简体中文</a> | English
+</div>
+
+### Model Introduction
+
+GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization. The model integrates the CogViT visual encoder pre-trained on large-scale image–text data, a lightweight cross-modal connector with efficient token downsampling, and a GLM-0.5B language decoder. Combined with a two-stage pipeline of layout analysis and parallel recognition based on PP-DocLayout-V3, GLM-OCR delivers robust and high-quality OCR performance across diverse document layouts.
+
+**Key Features**
+
+- **State-of-the-Art Performance**: Achieves a score of 94.62 on OmniDocBench V1.5, ranking #1 overall, and delivers state-of-the-art results across major document understanding benchmarks, including formula recognition, table recognition, and information extraction.
+
+- **Optimized for Real-World Scenarios**: Designed and optimized for practical business use cases, maintaining robust performance on complex tables, code-heavy documents, seals, and other challenging real-world layouts.
+
+- **Efficient Inference**: With only 0.9B parameters, GLM-OCR supports deployment via vLLM, SGLang, and Ollama, significantly reducing inference latency and compute cost, making it ideal for high-concurrency services and edge deployments.
+
+- **Easy to Use**: Fully open-sourced and equipped with a comprehensive [SDK](https://github.com/zai-org/GLM-OCR) and inference toolchain, offering simple installation, one-line invocation, and smooth integration into existing production pipelines.
+
+### News & Updates
+
+- **[2026.3.12]** GLM-OCR Technical Report is now available. See: [GLM-OCR Technical Report](https://arxiv.org/abs/2603.10910)
+- **[2026.2.12]** Fine-tuning tutorial based on LLaMA-Factory is now available. See: [GLM-OCR Fine-tuning Guide](examples/finetune/README.md)
+
+### Download Model
+
+| Model   | Download Links                                                                                                              | Precision |
+| ------- | --------------------------------------------------------------------------------------------------------------------------- | --------- |
+| GLM-OCR | [🤗 Hugging Face](https://huggingface.co/zai-org/GLM-OCR)<br> [🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/GLM-OCR) | BF16      |
+
+## GLM-OCR SDK
+
+We provide an SDK for using GLM-OCR more efficiently and conveniently.
+
+### Install SDK
+
+> [UV Installation](https://docs.astral.sh/uv/getting-started/installation/)
+
+```bash
+# Install from source
+git clone https://github.com/zai-org/glm-ocr.git
+cd glm-ocr
+uv venv --python 3.12 --seed && source .venv/bin/activate
+uv pip install -e .
+```
+
+### Model Deployment
+
+Two ways to use GLM-OCR:
+
+#### Option 1: Zhipu MaaS API (Recommended for Quick Start)
+
+Use the hosted cloud API – no GPU needed. The cloud service runs the complete GLM-OCR pipeline internally, so the SDK simply forwards your request and returns the result.
+
+1. Get an API key from https://open.bigmodel.cn
+2. Configure `config.yaml`:
+
+```yaml
+pipeline:
+  maas:
+    enabled: true # Enable MaaS mode
+    api_key: your-api-key # Required
+```
+
+That's it! When `maas.enabled=true`, the SDK acts as a thin wrapper that:
+
+- Forwards your documents to the Zhipu cloud API
+- Returns the results directly (Markdown + JSON layout details)
+- No local processing, no GPU required
+
+Input note (MaaS): the upstream API accepts `file` as a URL or a `data:<mime>;base64,...` data URI.
+If you have raw base64 without the `data:` prefix, wrap it as a data URI (recommended). The SDK will
+auto-wrap local file paths / bytes / raw base64 into a data URI when calling MaaS.
+
+API documentation: https://docs.bigmodel.cn/cn/guide/models/vlm/glm-ocr
+
+#### Option 2: Self-host with vLLM / SGLang
+
+Deploy the GLM-OCR model locally for full control. The SDK provides the complete pipeline: layout detection, parallel region OCR, and result formatting.
+
+##### Using vLLM
+
+Install vLLM:
+
+```bash
+uv pip install -U vllm --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly
+# Or use Docker
+docker pull vllm/vllm-openai:nightly
+```
+
+Launch the service:
+
+```bash
+# In docker container, uv may not be need for transformers install
+uv pip install git+https://github.com/huggingface/transformers.git
+
+# Run with MTP for better performance
+vllm serve zai-org/GLM-OCR --allowed-local-media-path / --port 8080 --speculative-config '{"method": "mtp", "num_speculative_tokens": 1}' --served-model-name glm-ocr
+```
+
+##### Using SGLang
+
+Install SGLang:
+
+```bash
+docker pull lmsysorg/sglang:dev
+# Or build from source
+uv pip install git+https://github.com/sgl-project/sglang.git#subdirectory=python
+```
+
+Launch the service:
+
+```bash
+# In docker container, uv may not be need for transformers install
+uv pip install git+https://github.com/huggingface/transformers.git
+
+# Run with MTP for better performance
+python -m sglang.launch_server --model zai-org/GLM-OCR --port 8080 --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --served-model-name glm-ocr
+# Modify the speculative config base on your device
+```
+
+##### Update Configuration
+
+After launching the service, configure `config.yaml`:
+
+```yaml
+pipeline:
+  maas:
+    enabled: false # Disable MaaS mode (default)
+  ocr_api:
+    api_host: localhost # or your vLLM/SGLang server address
+    api_port: 8080
+```
+
+#### Option 3: Ollama/MLX
+
+For specialized deployment scenarios, see the detailed guides:
+
+- **[Apple Silicon with mlx-vlm](examples/mlx-deploy/README.md)** - Optimized for Apple Silicon Macs
+- **[Ollama Deployment](examples/ollama-deploy/README.md)** - Simple local deployment with Ollama
+
+### SDK Usage Guide
+
+#### CLI
+
+```bash
+# Parse a single image
+glmocr parse examples/source/code.png
+
+# Parse a directory
+glmocr parse examples/source/
+
+# Set output directory
+glmocr parse examples/source/code.png --output ./results/
+
+# Use a custom config
+glmocr parse examples/source/code.png --config my_config.yaml
+
+# Enable debug logging with profiling
+glmocr parse examples/source/code.png --log-level DEBUG
+```
+
+#### Python API
+
+```python
+from glmocr import GlmOcr, parse
+
+# Simple function
+result = parse("image.png")
+result = parse(["img1.png", "img2.jpg"])
+result = parse("https://example.com/image.png")
+result.save(output_dir="./results")
+
+# Note: a list is treated as pages of a single document.
+
+# Class-based API
+with GlmOcr() as parser:
+    result = parser.parse("image.png")
+    print(result.json_result)
+    result.save()
+```
+
+#### Flask Service
+
+```bash
+# Start service
+python -m glmocr.server
+
+# With debug logging
+python -m glmocr.server --log-level DEBUG
+
+# Call API
+curl -X POST http://localhost:5002/glmocr/parse \
+  -H "Content-Type: application/json" \
+  -d '{"images": ["./example/source/code.png"]}'
+```
+
+Semantics:
+
+- `images` can be a string or a list.
+- A list is treated as pages of a single document.
+- For multiple independent documents, call the endpoint multiple times (one document per request).
+
+### Configuration
+
+Full configuration in `glmocr/config.yaml`:
+
+```yaml
+# Server (for glmocr.server)
+server:
+  host: "0.0.0.0"
+  port: 5002
+  debug: false
+
+# Logging
+logging:
+  level: INFO # DEBUG enables profiling
+
+# Pipeline
+pipeline:
+  # OCR API connection
+  ocr_api:
+    api_host: localhost
+    api_port: 8080
+    api_key: null # or set API_KEY env var
+    connect_timeout: 300
+    request_timeout: 300
+
+  # Page loader settings
+  page_loader:
+    max_tokens: 16384
+    temperature: 0.01
+    image_format: JPEG
+    min_pixels: 12544
+    max_pixels: 71372800
+
+  # Result formatting
+  result_formatter:
+    output_format: both # json, markdown, or both
+
+  # Layout detection (optional)
+  enable_layout: false
+```
+
+See [config.yaml](glmocr/config.yaml) for all options.
+
+### Output Formats
+
+Here are two examples of output formats:
+
+- JSON
+
+```json
+[[{ "index": 0, "label": "text", "content": "...", "bbox_2d": null }]]
+```
+
+- Markdown
+
+```markdown
+# Document Title
+
+Body...
+
+| Table | Content |
+| ----- | ------- |
+| ...   | ...     |
+```
+
+### Example of full pipeline
+
+you can run example code like：
+
+```bash
+python examples/example.py
+```
+
+Output structure (one folder per input):
+
+- `result.json` – structured OCR result
+- `result.md` – Markdown result
+- `imgs/` – cropped image regions (when layout mode is enabled)
+
+### Modular Architecture
+
+GLM-OCR uses composable modules for easy customization:
+
+| Component             | Description                            |
+| --------------------- | -------------------------------------- |
+| `PageLoader`          | Preprocessing and image encoding       |
+| `OCRClient`           | Calls the GLM-OCR model service        |
+| `PPDocLayoutDetector` | PP-DocLayout layout detection          |
+| `ResultFormatter`     | Post-processing, outputs JSON/Markdown |
+
+You can extend the behavior by creating custom pipelines:
+
+```python
+from glmocr.dataloader import PageLoader
+from glmocr.ocr_client import OCRClient
+from glmocr.postprocess import ResultFormatter
+
+
+class MyPipeline:
+  def __init__(self, config):
+    self.page_loader = PageLoader(config)
+    self.ocr_client = OCRClient(config)
+    self.formatter = ResultFormatter(config)
+
+  def process(self, request_data):
+    # Implement your own processing logic
+    pass
+```
+
+## Acknowledgement
+
+This project is inspired by the excellent work of the following projects and communities:
+
+- [PP-DocLayout-V3](https://huggingface.co/PaddlePaddle/PP-DocLayoutV3)
+- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
+- [MinerU](https://github.com/opendatalab/MinerU)
+
+## License
+
+The Code of this repo is under Apache License 2.0.
+
+The GLM-OCR model is released under the MIT License.
+
+The complete OCR pipeline integrates [PP-DocLayoutV3](https://huggingface.co/PaddlePaddle/PP-DocLayoutV3) for document layout analysis, which is licensed under the Apache License 2.0. Users should comply with both licenses when using this project.
+
+## Citation
+
+If you find GLM-OCR useful in your research, please cite our technical report:
+
+```bibtex
+@misc{duan2026glmocrtechnicalreport,
+      title={GLM-OCR Technical Report},
+      author={Shuaiqi Duan and Yadong Xue and Weihan Wang and Zhe Su and Huan Liu and Sheng Yang and Guobing Gan and Guo Wang and Zihan Wang and Shengdong Yan and Dexin Jin and Yuxuan Zhang and Guohong Wen and Yanfeng Wang and Yutao Zhang and Xiaohan Zhang and Wenyi Hong and Yukuo Cen and Da Yin and Bin Chen and Wenmeng Yu and Xiaotao Gu and Jie Tang},
+      year={2026},
+      eprint={2603.10910},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2603.10910},
+}
+```