{"id":29561634,"url":"https://github.com/flagopen/scisage","last_synced_at":"2025-07-18T16:39:05.630Z","repository":{"id":305096321,"uuid":"1000953045","full_name":"FlagOpen/SciSage","owner":"FlagOpen","description":"official repo of SciSage","archived":false,"fork":false,"pushed_at":"2025-07-18T06:23:11.000Z","size":13592,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-18T10:28:11.129Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FlagOpen.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-12T15:18:17.000Z","updated_at":"2025-07-18T06:23:14.000Z","dependencies_parsed_at":"2025-07-18T10:42:25.682Z","dependency_job_id":null,"html_url":"https://github.com/FlagOpen/SciSage","commit_stats":null,"previous_names":["flagopen/scisage"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/FlagOpen/SciSage","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlagOpen%2FSciSage","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlagOpen%2FSciSage/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlagOpen%2FSciSage/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlagOpen%2FSciSage/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FlagOpen","download_url":"https://codeload.github.com/FlagOpen/SciSage/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FlagOpen%2FSciSage/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265793684,"owners_count":23829180,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-07-18T16:39:05.115Z","updated_at":"2025-07-18T16:39:05.619Z","avatar_url":"https://github.com/FlagOpen.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SciSage\n\nAn intelligent academic paper analysis system that leverages AI to understand research papers and generate comprehensive analysis reports.\n\n📄 **Paper**: https://arxiv.org/abs/2506.12689\n\n📊 **Benchmark**: https://huggingface.co/datasets/BAAI/SurveyScope\n\n## Features\n\n- **Multi-source Paper Extraction**: Robust crawling from arXiv with fallback mechanisms\n- **Intelligent Analysis**: AI-powered paper understanding and outline generation\n- **Structured Content Generation**: Section-wise detailed analysis with proper citations\n- **Multi-model Support**: Compatible with GPT-4, local models, and cloud services\n\n## Quick Start\n\n### 1. Installation\n```bash\ngit clone https://github.com/your-repo/SciSage.git\ncd SciSage\npip install -r requirements.txt\n```\n\n### 2. Configuration\n```bash\n# Configure models in core/model_factory.py\n# Set API keys and endpoints in core/configuration.py\n```\n\n\n### 4. Run Analysis\n```bash\ncd core\npython main_workflow_opt_for_paper.py\n```\n\n\n## Project Structure\n\n```\nSciSage/\n├── benchmark/              # Paper extraction tools\n│   └── get_paper_info.py   # Multi-source paper crawler for benchmark build\n├── core/                   # Analysis pipeline\n│   ├── main_workflow_opt_for_paper.py  # Main orchestrator\n│   ├── paper_outline_opt.py            # Outline generation\n│   ├── paper_poolish_opt.py            # Content polishing\n│   ├── model_factory.py                # Model management\n│   └── configuration.py                # Settings\n└── eval/                   # Evaluation tools\n```\n\n## Configuration\n\n### Model Setup\nEdit [`core/model_factory.py`](core/model_factory.py):\n```python\nllm_map = {\n    \"gpt-4\": AzureChatOpenAI(...),\n    \"gpt-4o-mini\": AzureChatOpenAI(...),\n}\n```\n\n### Pipeline Settings\nEdit [`core/configuration.py`](core/configuration.py):\n```python\nOUTLINE_GENERATION_MODEL = \"gpt-4o-mini\"\nCONTENT_GENERATION_MODEL = \"gpt-4\"\nREFLECTION_MODEL = \"gpt-4\"\n```\n\n## Example Usage\n\n```python\n# Extract paper information\nfrom benchmark.get_paper_info import process_arxiv_papers\n\narxiv_urls = [\"https://arxiv.org/abs/2306.11646\"]\nawait process_arxiv_papers(arxiv_urls, \"papers.jsonl\")\n\n# Run analysis pipeline\nfrom core.main_workflow_opt_for_paper import run_analysis_pipeline\n\nresult = run_analysis_pipeline(\n    paper_data=\"paper_content.json\",\n    output_path=\"analysis_output.json\"\n)\n```\n\n## Requirements\n\n- Python 3.8+\n- langchain, arxiv, requests\n- See [`requirements.txt`](requirements.txt) for full dependencies\n\n## License\n\nMIT License - see LICENSE file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflagopen%2Fscisage","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fflagopen%2Fscisage","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflagopen%2Fscisage/lists"}