How Iusora scores.
Every finding is independently retrieved by five language models. Where multiple readers corroborate the same passage, the result enters the report with a high quorum coefficient. Where they disagree, we surface the disagreement — we never silently break ties.
Quorum routing
Five independent readers — Claude, Gemini, Mistral, Poolside, and GPT-4o — run in parallel on each claim element. A finding is confirmed when multiple vendors cite the same prior-art paragraph; single-vendor findings are surfaced and explicitly labeled in the report export, never silently resolved.
Thresholds are tenant-configurable. Forensic mode adds source URLs, paragraph citations, and per-vendor attribution in every DOCX export.
Citations & auditability
Each cited reference includes its exact paragraph or column-line citation, exportable to Word with hyperlinks intact. We benchmark retrieval against the EPO Boards of Appeal corpus quarterly; benchmark commits are timestamped in the public repo.
Transparency commitments
- Routing logic and evaluation harnesses are published — no proprietary black box scoring.
- Subprocessors are listed by name with EU residency status on /subprocessors and updated within five business days of any change.
- We do not hide which model wrote which passage when forensic mode is enabled.