{"id":51220949,"url":"https://github.com/sankhya007/research_paper_hunter","last_synced_at":"2026-06-28T07:03:05.632Z","repository":{"id":346525999,"uuid":"1190359889","full_name":"sankhya007/research_paper_hunter","owner":"sankhya007","description":"this is made to help my main project, basically helping me go through research paper a lot faster than manual reading","archived":false,"fork":false,"pushed_at":"2026-03-25T07:50:25.000Z","size":4370,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-25T10:07:38.166Z","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":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sankhya007.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-24T07:56:45.000Z","updated_at":"2026-03-25T07:20:37.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/sankhya007/research_paper_hunter","commit_stats":null,"previous_names":["sankhya007/research_paper_hunter"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/sankhya007/research_paper_hunter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fresearch_paper_hunter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fresearch_paper_hunter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fresearch_paper_hunter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fresearch_paper_hunter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sankhya007","download_url":"https://codeload.github.com/sankhya007/research_paper_hunter/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fresearch_paper_hunter/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34880191,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-28T02:00:05.809Z","response_time":54,"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":[],"created_at":"2026-06-28T07:03:04.463Z","updated_at":"2026-06-28T07:03:05.615Z","avatar_url":"https://github.com/sankhya007.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Research Paper Bot\n\n## Overview\n\nResearch Paper Bot is a modular, domain-agnostic research assistant designed to automate the discovery, filtering, and analysis of academic research papers.\n\nThe system integrates multiple research sources (Semantic Scholar and arXiv), applies keyword-driven contextual filtering, and extracts structured insights such as methodologies, formulas, and implementation ideas.\n\nIt is built to support both targeted research (e.g., crowd evacuation modeling) and general-purpose exploration across multiple domains including artificial intelligence, robotics, healthcare, and systems engineering.\n\n---\n\n## Core Objectives\n\n* Reduce time spent manually reading research papers\n* Extract only the most relevant information based on user intent\n* Provide structured insights that can be directly implemented\n* Enable domain-specific research workflows through presets\n\n---\n\n## Key Capabilities\n\n### 1. Multi-Source Paper Retrieval\n\n* Queries Semantic Scholar API\n* Falls back to arXiv for reliable PDF access\n* Supports user-defined number of papers\n\n### 2. Interactive Paper Selection\n\n* Displays indexed list of papers\n* Allows selective processing instead of bulk analysis\n\n### 3. Keyword-Driven Contextual Filtering\n\n* Extracts only relevant portions of text based on:\n\n  * preset keyword sets\n  * custom user-defined keywords\n* Includes context window for better understanding\n\n### 4. Domain-Adaptive Preset System\n\nSupports 50+ domains including:\n\n* Crowd dynamics (panic, congestion, hazard)\n* Machine learning, deep learning\n* Robotics and control systems\n* Computer vision and NLP\n* Distributed systems and networking\n* Mathematics and simulation\n* Healthcare and bioinformatics\n* Finance and economics\n\n### 5. Insight Extraction Engine\n\nIdentifies:\n\n* Models and methodologies\n* Algorithms and approaches\n* Experimental results\n* Implementation-related content\n\n### 6. Formula Detection\n\n* Extracts mathematical expressions and equations\n* Useful for simulation and modeling tasks\n\n### 7. Implementation Generator\n\n* Converts insights into:\n\n  * pseudo-code\n  * actionable ideas\n  * difficulty estimates\n\n### 8. Persistent Storage System\n\n* Saves results per paper in structured folders\n* Maintains history of downloaded papers\n* Supports re-download control\n\n---\n\n## System Architecture\n\nThe system follows a modular pipeline:\n\nUser Input → Search → Selection → Extraction → Processing → Output\n\n### Detailed Flow\n\n1. User Input\n\n   * Topic\n   * Number of papers\n   * Mode (preset or custom keywords)\n\n2. Search Layer\n\n   * Semantic Scholar API\n   * arXiv API fallback\n   * Deduplication of results\n\n3. Selection Layer\n\n   * Indexed paper display\n   * Manual user selection\n\n4. Processing Layer\n\n   * PDF download\n   * Text extraction\n   * Keyword filtering with context\n   * Insight extraction\n   * Formula detection\n   * Implementation generation\n\n5. Output Layer\n\n   * Structured text files\n   * CSV summary\n\n---\n\n## Project Structure\n\n```\nresearch_paper_bot/\n│\n├── main.py                # Entry point and orchestration\n├── search.py              # API integration and paper retrieval\n├── parser.py              # PDF parsing and text extraction\n├── analyzer.py            # Insight extraction and filtering\n├── extractor.py           # Implementation idea generation\n├── scorer.py              # Paper scoring logic\n├── utils.py               # Utility functions (download, save, history)\n├── presets.py             # Keyword preset definitions\n├── memory.py              # Processed paper tracking\n│\n├── requirements.txt\n├── README.md\n├── LICENSE\n├── .gitignore\n│\n└── output/                # Generated outputs (ignored in Git)\n```\n\n---\n\n## Installation\n\nClone the repository:\n\n```bash\ngit clone https://github.com/sankhya007/research_paper_hunter.git\ncd research_paper_hunter\n```\n\nInstall dependencies:\n\n```bash\npip install -r requirements.txt\n```\n\n---\n\n## Usage Guide\n\nRun the program:\n\n```bash\npython main.py\n```\n\n### Step 1: Select Mode\n\n```\n1. Search new papers\n2. View downloaded papers\n```\n\n---\n\n### Step 2: Enter Inputs\n\nExample:\n\n```\nTopic: crowd evacuation\nHow many papers: 20\nMode: panic\n```\n\n---\n\n### Step 3: Select Papers\n\n```\n[0] Paper A\n[1] Paper B\n[2] Paper C\n...\n\nEnter indices:\n1 2 5\n```\n\n---\n\n### Step 4: Processing\n\nFor each selected paper:\n\n* PDF is downloaded\n* Text is extracted\n* Relevant sections are filtered\n* Insights and formulas are extracted\n* Implementation ideas are generated\n\n---\n\n## Output Format\n\nEach paper generates:\n\n```\noutput/\u003cpaper_name\u003e/\n    important.txt\n```\n\n### important.txt contains:\n\n* Important insights\n* Extracted formulas\n* Implementation ideas with pseudo-code\n\nAdditionally:\n\n```\noutput/results.csv\n```\n\nContains a summary of all processed papers.\n\n---\n\n## Keyword Filtering Mechanism\n\nThe system filters text using:\n\n* Keyword matching (case-insensitive)\n* Context window expansion (±2 lines)\n\nExample:\n\nIf keyword = \"panic\"\n\nExtracted content:\n\n* Lines containing \"panic\"\n* Surrounding context for better understanding\n\n---\n\n## Extending the System\n\n### Adding New Presets\n\nEdit `presets.py`:\n\n```\n\"your_domain\": [\"keyword1\", \"keyword2\", ...]\n```\n\n---\n\n### Modifying Insight Extraction\n\nEdit `analyzer.py`:\n\n* Add new patterns\n* Improve filtering logic\n\n---\n\n### Enhancing Implementation Generator\n\nEdit `extractor.py`:\n\n* Add domain-specific pseudo-code generation\n* Improve difficulty estimation\n\n---\n\n## Limitations\n\n* Some papers may not provide downloadable PDFs\n* PDF parsing may fail for scanned documents\n* Semantic Scholar API may rate-limit requests\n* Keyword filtering depends on text quality\n\n---\n\n## Future Improvements\n\n* API retry and caching system\n* Insight ranking based on importance\n* Keyword highlighting in outputs\n* GUI-based interface\n* Integration with simulation systems (e.g., TRAGIC)\n* Automated mapping of insights to executable models\n\n---\n\n## Use Cases\n\n* Research students extracting key insights quickly\n* Simulation developers building models from papers\n* AI practitioners exploring new methodologies\n* Cross-domain literature analysis\n\n---\n\n## Author\n\nSankhyapriyo Dey\n\n---\n\n## License\n\nThis project is licensed under the MIT License.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsankhya007%2Fresearch_paper_hunter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsankhya007%2Fresearch_paper_hunter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsankhya007%2Fresearch_paper_hunter/lists"}