What exactly is AiVIS Cite Ledger?

AiVIS Cite Ledger is an evidence-backed AI citation audit and remediation system. It measures how AI models, ChatGPT, Perplexity, Claude, and Google AI, interpret, trust, and cite your web content. The result is a 0–100 CITE LEDGER score across ten weighted families (avs-v3), with BRAG evidence-linked findings and prioritized fixes.

How is this different from Semrush, Ahrefs, or Clearscope?

Traditional SEO tools optimize for keyword ranking in traditional search results. AiVIS Cite Ledger audits citation readiness, the specific signals that determine whether AI answer engines retrieve and cite your content. A page can rank #1 on Google and be completely invisible to AI answer synthesis.

What is BRAG and how does it make findings trustworthy?

BRAG stands for Based-Retrieval-Auditable-Grading. It ties every audit finding to a real, traceable element on your page, a specific heading, schema block, meta tag, or content section, each carrying a unique evidence ID. You can open the element, verify the finding, and recheck it after a fix. No black boxes.

Is the free tier genuinely useful, or just a teaser?

The Observer (free) plan gives you a full composite CITE LEDGER score and all ten family scores (avs-v3), so you can see exactly where you stand and which categories are hurting you. BRAG evidence IDs and prioritized fix packs require a paid plan. Three audits per month, no credit card.

Citation Content Scoring Rubric: Weighted Criteria Aligned to the 15 BRAG Factors | AiVIS Cite Ledger Blogs

By Founder, AiVIS Cite Ledger · 2026-06-11 · 14 min read · IMPLEMENTATION

Not all checklist items are equal. A page can check every box under "internal linking" and still fail on entity resolution — the one factor that accounts for whether anything else you built gets credited to you. This rubric makes the weights explicit.

Key Takeaways

Entity resolution and extractability act as multipliers — a zero on either drags the total regardless of other scores.
The scoring floor rule makes it impossible to hide a structural failure behind strong section scores.
Benchmark calibration against Stripe, Cloudflare, and Supabase shows typical score ranges for citation-ready content.
The rubric maps directly to BRAG audit findings so scores are comparable across the platform.

Article

# Citation Content Scoring Rubric: Weighted Criteria Aligned to the 15 BRAG Factors

The citation-optimized content checklist tells you what to do. This rubric tells you how much each item matters.

The weights here are calibrated to the 15 BRAG measurement criteria — the same signal surface the AiVIS platform probes when it grades a page. Use this rubric when you need to prioritize a fix backlog, audit a client page against a competitor, or explain why a page scores 68 instead of 91.

How to read the rubric

Each criterion carries a maximum point value. Score each item from 0 to its maximum. A page scoring below 60 across all criteria is typically below the citation threshold for competitive queries. A page scoring above 80 is in citation-eligible territory — provided the highest-weight items are not zeroed out.

**Critical rule:** entity resolution (criterion 1) and extractability (criterion 2) act as partial multipliers. A zero on either drags the entire score down even if every other item is maxed. This mirrors what happens in production: a page with flawless schema but no defined entity still gets its citations credited to someone else.

The rubric

Criterion 1 — Entity Resolution (20 points)

**What it measures:** Can the model reliably identify your organization, person, or product as a distinct entity and connect it to your domain?

| Item | Max | How to score |

|---|---|---|

| Primary entity is named, defined, and consistent across the page | 6 | 0 = absent, 3 = present but inconsistent, 6 = consistent + linked to schema |

| Entity has a defined type (Organization, Person, Product) in JSON-LD | 4 | 0 = absent, 2 = present but incomplete, 4 = complete with sameAs/url |

| Entity appears in the first 200 words | 4 | 0/4 binary |

| Entity is referenced consistently (no synonym drift) | 3 | 0 = drift detected, 3 = clean |

| Related entities are named and their relationship to the primary entity is stated | 3 | 0 = absent, 1–3 = partial to complete |

Enable JavaScript for the full interactive reading experience with related articles and discussion.