{"id":31767653,"url":"https://github.com/bits-bytes-nn/scholar-lens","last_synced_at":"2026-05-16T17:39:48.456Z","repository":{"id":318201508,"uuid":"1068519120","full_name":"bits-bytes-nn/scholar-lens","owner":"bits-bytes-nn","description":"A tool that generates comprehensive and in-depth reviews of AI/ML research papers using generative AI technology. Check out my tech blog: https://bits-bytes-nn.github.io/","archived":false,"fork":false,"pushed_at":"2025-10-05T18:10:25.000Z","size":9160,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-05T20:23:59.525Z","etag":null,"topics":["amazon-bedrock","amazon-sns","aws-batch","aws-cdk","langchain","langgraph","poetry"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bits-bytes-nn.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-02T14:02:35.000Z","updated_at":"2025-10-05T18:10:30.000Z","dependencies_parsed_at":"2025-10-05T20:24:22.182Z","dependency_job_id":"1c8b1067-a25e-4f9b-9fc5-12e5fb954957","html_url":"https://github.com/bits-bytes-nn/scholar-lens","commit_stats":null,"previous_names":["bits-bytes-nn/scholar-lens"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/bits-bytes-nn/scholar-lens","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bits-bytes-nn%2Fscholar-lens","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bits-bytes-nn%2Fscholar-lens/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bits-bytes-nn%2Fscholar-lens/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bits-bytes-nn%2Fscholar-lens/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bits-bytes-nn","download_url":"https://codeload.github.com/bits-bytes-nn/scholar-lens/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bits-bytes-nn%2Fscholar-lens/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279002398,"owners_count":26083373,"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","status":"online","status_checked_at":"2025-10-09T02:00:07.460Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["amazon-bedrock","amazon-sns","aws-batch","aws-cdk","langchain","langgraph","poetry"],"created_at":"2025-10-10T01:18:34.820Z","updated_at":"2026-05-16T17:39:48.450Z","avatar_url":"https://github.com/bits-bytes-nn.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## 👩‍🏫 SCHOLAR-LENS\n\nAI-powered academic paper review assistant that generates comprehensive analyses of arXiv papers through intelligent content extraction, citation analysis, and code repository integration.\n\n![Sample](./assets/sample.png)\n\n### ✨ Features\n\n- **AI-Powered Analysis**: Uses Amazon Bedrock (Claude models) for multi-stage paper understanding\n- **Multi-Source Processing**: Extracts content from arXiv HTML/PDF, analyzes citations, and reviews code repositories\n- **Scalable Infrastructure**: AWS Batch for containerized job execution\n- **Intelligent Extraction**: Figure analysis, table of contents generation, and citation mapping\n- **Code Integration**: GitHub repository analysis with semantic search via FAISS\n\n### 🏗️ Architecture\n\n#### Core Components\n- **ArxivHandler** (`arxiv_handler.py`): Paper metadata and content retrieval\n- **Parser** (`parser.py`): HTML/PDF parsing with figure extraction\n- **ContentExtractor** (`content_extractor.py`): Structured content and citation extraction\n- **CodeRetriever** (`code_retriever.py`): Repository cloning and semantic code analysis\n- **CitationSummarizer** (`citation_summarizer.py`): Reference paper analysis\n- **ExplainerGraph** (`explainer.py`): Multi-stage LangGraph workflow for paper synthesis\n\n#### Infrastructure\n- **AWS Batch**: Containerized job execution with ECS\n- **Amazon Bedrock**: Claude models for analysis and generation\n- **S3**: Paper storage and asset management\n- **SSM Parameter Store**: Configuration management\n\n### 🛠️ Tech Stack\n\n- Python 3.12+, AWS CDK, Docker\n- Amazon Bedrock, LangChain, LangGraph\n- PyMuPDF, BeautifulSoup4, FAISS\n- Pydantic validation, YAML configuration\n\n### 📋 Configuration\n\nCreate `scholar_lens/configs/config.yaml`:\n\n```yaml\nresources:\n  project_name: scholar-lens\n  stage: dev\n  profile_name: your-profile\n  default_region_name: ap-northeast-2\n  bedrock_region_name: us-west-2\n  s3_bucket_name: your-bucket\n  email_address: your-email@example.com\n\npaper:\n  citation_extraction_model_id: anthropic.claude-sonnet-4-5-20250929-v1:0\n  table_of_contents_model_id: anthropic.claude-sonnet-4-5-20250929-v1:0\n\nexplanation:\n  paper_analysis_model_id: anthropic.claude-sonnet-4-5-20250929-v1:0\n  paper_synthesis_model_id: anthropic.claude-sonnet-4-5-20250929-v1:0\n```\n\n### 🚀 Usage\n\n#### Infrastructure Deployment\n```bash\n# Deploy infrastructure\npython scripts/deploy_infra.py\n```\n\n#### Development\n```bash\n# Install dependencies\npoetry install\n\n# Set up environment\ncp .env.template .env\n# Edit .env with your configuration\n\n# Run locally\npython scholar_lens/main.py --arxiv-id 2312.11805 --parse-pdf True\n\n# Submit batch job\npython scripts/run_batch.py --arxiv-id 2505.09388 --repo-urls http://arxiv.org/pdf/2505.09388v1\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbits-bytes-nn%2Fscholar-lens","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbits-bytes-nn%2Fscholar-lens","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbits-bytes-nn%2Fscholar-lens/lists"}