BiasClear

BiasClear is open-source structural persuasion detection infrastructure for the AI ecosystem. It audits text for rhetorical manipulation patterns such as manufactured consensus, authority substitution, false urgency, and dissent dismissal—patterns that sentiment, toxicity, and fact-checking tools do not target well. The system combines a deterministic frozen core of 42 hand-authored detection patterns across legal, media, financial, and general domains with governed LLM-assisted analysis, SHA-256 hash-chained auditability, and a live public deployment at biasclear.com. Funding would support validation, independent security review, and broader adoption of this public-interest governance layer.