Deploy OpenStudy Gradio Space

.gitignore

@@ -0,0 +1,8 @@
+__pycache__/
+*.pyc
+.DS_Store
+.venv/
+venv/
+.env
+*.egg-info/
+.gstack/

GRADIO_REQUIREMENT.md

@@ -0,0 +1,27 @@
+# Gradio Requirement
+
+OpenStudy must be built with Gradio.
+
+All user-facing application features must run through a Gradio interface so the project works directly on Hugging Face Spaces with the Gradio SDK.
+
+## Required Implementation
+
+- The main app entry point must be `app.py`.
+- The Hugging Face Space metadata must use `sdk: gradio`.
+- Dependencies must be listed in `requirements.txt`.
+- Search, upload, project review, tables, plots, downloads, and reports must be exposed through Gradio components.
+- The app should launch with `demo.launch()` or an equivalent Gradio launch wrapper.
+
+## Not Allowed As Replacements
+
+- Do not replace the Gradio app with Streamlit, Flask, Django, FastAPI-only pages, React, Next.js, or another frontend framework.
+- Do not move the primary user experience outside Gradio.
+- Backend helpers are allowed only when they support the Gradio app.
+
+## Deployment Target
+
+The app must remain compatible with Hugging Face Spaces using the Gradio SDK.
+
+## AI Model Requirement
+
+Any AI agent review must use `Qwen/Qwen3.6-27B` only. Do not add fallback models or alternate LLM providers.

README.md

@@ -1,13 +1,46 @@
 ---
 title: OpenStudy
-emoji: 🐠
-colorFrom: gray
-colorTo: pink
+emoji: 🔬
+colorFrom: green
+colorTo: yellow
 sdk: gradio
-sdk_version: 6.18.0
-python_version: '3.13'
 app_file: app.py
 pinned: false
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# OpenStudy
+
+OpenStudy is an open-source Gradio app for screening research studies for reported bias controls, study conduct details, ethics safeguards, funding disclosures, and transparency signals.
+
+Users can:
+
+- Search public study metadata by DOI, URL, title, or keywords, returning at least 15 papers per topic when public metadata sources have enough matches, and evaluate a result with one click.
+- Evaluate abstracts and available metadata from public sources, with plain-language explanations of what every score and category means.
+- Define their own screening standards and parameters (categories that count, safeguards that must be reported, a minimum score, adjustable risk thresholds, and custom required terms) and get a pass/fail verdict against them on every evaluation.
+- Add their own research study (PDF, DOCX, text, or pasted manuscript) to screen it for bias-control and credibility safeguards against those standards.
+- Upload their own research projects, protocols, benchmark plans, or preregistrations to review planned conduct before or during a study.
+- Keep an in-session project dashboard and export project summaries as JSON.
+- Run an optional Qwen agent review using `Qwen/Qwen3.6-27B` only.
+- Download a Markdown report with evidence snippets and follow-up questions.
+
+## Required AI model
+
+OpenStudy's AI review path is restricted to `Qwen/Qwen3.6-27B` only. It does not fall back to another model.
+
+For Hugging Face Spaces, configure a Space secret named `HF_TOKEN` with access to the model or paste a temporary token into the Qwen review control in the app.
+
+## Important limitation
+
+OpenStudy is a decision-support checklist. It flags what appears to be reported or missing in the supplied text. It does not certify that a study is ethical, unethical, biased, unbiased, valid, or invalid.
+
+## Run locally
+
+```bash
+pip install -r requirements.txt
+python app.py
+```
+
+## Deploy on Hugging Face Spaces
+
+Create a new Space using the Gradio SDK, then upload this repository. Hugging Face Spaces installs `requirements.txt` and runs `app.py`.

requirements.txt

@@ -0,0 +1,7 @@
+gradio>=4.44.1
+huggingface_hub>=0.33.5
+requests>=2.32.0
+beautifulsoup4>=4.12.0
+pypdf>=4.3.0
+python-docx>=1.1.2
+matplotlib>=3.8.0