Autonomous AI-powered academic research system.
-
Updated
Jun 22, 2026 - Python
8000
Autonomous AI-powered academic research system.
Turn any web page into traceable, citable evidence for AI agents.
Implementation of feature-based CRF for evidence fragment detection described in EACL 2021 paper "Scientific Discourse Tagging for Evidence Extraction"
Evidence-grounded, multi-agent research assistant that performs RAG over scientific papers, extracts structured claims, builds a Neo4j knowledge graph, and answers questions with verifiable citations and stateful session memory.
An AI-assisted pipeline for automating biomedical literature discovery, full-text processing, genomic variant extraction, evidence annotation, and ClinVar-based validation.
Real time monitoring and evidence extraction tool for MySql Shell to detect suspicious activity from internal members.
Deterministic extraction and evaluation of harms evidence in total knee arthroplasty randomized trials
Automated research paper analysis: PDF → JSON with evidence extraction using LLMs (DeepSeek, Gemma). Extracts methods, results, datasets, and claims with precise evidence grounding.
Rust conflict-intelligence engine that extracts actors, claims, commitments, contradictions, friction patterns, and evidence spans from messy text.
Five-agent LangGraph system for automated scientific paper ingestion, citation graph analysis, evidence extraction, conflict detection, and research synthesis using FastAPI, PostgreSQL, and Streamlit
Browser automation research agent with evidence extraction and source scoring.
Grounded clinical evidence extraction for policy review. The model selects citations by ID; code slices them from the record, so a fabricated snippet is structurally impossible.
A non-invasive forensic tool for extracting, analyzing, and managing evidence from WearOS smartwatches. Placed 4th at CIDECODE 2.0
Add a description, image, and links to the evidence-extraction topic page so that developers can more easily learn about it.
To associate your repository with the evidence-extraction topic, visit your repo's landing page and select "manage topics."