Flamehaven-Veritas
VERITAS — AI Critique Experimental Report Analysis Framework | 7-phase scientific paper critique engine with LOGOS, MICA, BMJ/KU templates
About This Work
A sovereignty-grade experimental report critique engine. Implements the VERITAS v2.2 protocol as a fully executable Python package + REST API + CLI.
Repository Overview
A sovereignty-grade experimental report critique engine. Implements the VERITAS v2.2 protocol as a fully executable Python package + REST API + CLI.
README Core
A sovereignty-grade experimental report critique engine. Implements the VERITAS v2.2 protocol as a fully executable Python package + REST API + CLI.
Accepts a raw experimental report (text, PDF, DOCX, MD) and produces a structured critique through a 7-phase pipeline, enriched with LOGOS reasoning, HSTA scoring, bibliography analysis, and reproducibility assessment.
All outputs use either the BMJ Scientific Editing template or the KU Research Report template (--template bmj|ku).
Use & Documentation
Detailed installation, commands, examples, and deeper usage notes live in the repository README and docs.
README Map
- AI Critique Experimental Report Analysis Framework
- What It Does
- Workflow
- Quick Start
- Python API
- CLI
Key Signals
- Total reference count and format detection (Vancouver / APA / Harvard)
- Year range (oldest → newest)
- Self-citation detection
- Quality score: 0.0–1.0 composite (recency 50% + breadth 50%, −10% if self-cites detected)
- Measured artifact / raw result file
Announcements
synced Apr 20, 2026