What does "configurable scoring" mean?
Gamut's Verification Confidence Score is computed from four dimensions: registry match, source diversity, cross-source consistency, and entity completeness. The dimensions are architectural — they define what verification means. What's configurable is the policy on top: how much each dimension weighs, which entity attributes count toward completeness, which risk flags are active, and what severity they carry. A PE/VC team weights registry match and source diversity highest. A compliance team weights registry match and cross-source consistency. An insurance underwriter cares about entity completeness and filing recency. Each configuration is a Scoring Template — a runtime policy loaded from config, not a code change. Bring your own risk framework; we verify the evidence underneath it.
What registries are covered?
Three government registries are live in production: Singapore (ACRA — every registered company), United Kingdom (Companies House — every active company), and United States (SEC EDGAR — every SEC filer). Each registry returns ground truth entity data at the highest confidence tier. Additional APAC jurisdictions (Thailand, Vietnam, Malaysia, Indonesia) are on the roadmap via AsiaVerify. Every new registry expands the verifiable universe across all verticals without pipeline changes.
What is intelligence compounding?
Every verification query enriches your entity dataset. Verified claims, confidence scores, source attributions, and risk flags are written back to an intelligence cache after every run. The second time you encounter an entity, the pipeline starts with everything it learned from the first encounter — registry status, funding data, founder details, HQ confirmation — before running a single new search. Query 1,000 produces better results than query 10, not because the AI model improved, but because the pipeline accumulated verified evidence over 999 prior runs. Your queries build your dataset. No competitor ran them, so no competitor has it.
Is there an open-source option?
Verity is a three-layer content authenticity detection pipeline, available under Apache 2.0. It handles source credibility scoring, relevance filtering, and authenticity detection for any topic you configure. The Gamut platform adds government registry verification, entity resolution, deterministic confidence scoring, configurable Scoring Templates, continuous monitoring via Sentinel, and the full IC Memo intelligence pipeline on top. Verity handles trust in content. Gamut handles trust in entities.