EEAT Mechanics

Topic

Quality & Prediction

The largest class, and the one that runs before ranking rather than during it: a set of models that predict how a human rater would score a page or a site. Most of what people mean by “E-E-A-T signals” lives here — and so does the calibration layer that decides what the predictions are trained against.

01Systems8

  • 06BQ* (Balance)Q* is a summary quality score for the entire website — a 'balance' made up of the site's authority (siteAuthority), a low-quality flag (lowQuality), and the overall NSR value. This score changes slowly: internal Google documents describe it as 'largely static' — a sluggish foundation, not a day-to-day signal.
  • 07B/CNSR (+ Fallback inheritance)NSR (Normalized Site Rank) is the real quality core — a normalized quality and authority value computed for individual 'chunks' (subsections) of a website. New sections initially inherit the average of their neighboring chunks ('fallback inheritance'). The historicized signal (predictedDefaultNsr) shows development over time — the trajectory matters, not today's single value.
  • 08Bchard (+ YMYL/Hoax)chard rates the content quality of individual pages — calibrated against the judgments of human quality raters that Google trains according to strict guidelines (QRG). A variance score shows how confident the model is in its verdict. chard is especially sharp on YMYL content (Your Money or Your Life — topics with real life consequences such as health, safety, severe weather) and on suspected misinformation.
  • 09BcontentEffortA language model estimates how much editorial effort and depth went into a page. The system distinguishes between shallow, machine-generated content and pages with recognizable research, structure and substance. It is not a hard measurement but a model estimate — one that increasingly reliably separates thin AI content from genuine editorial engagement.
  • 10B/Ctofu / keto / Rhubarb / SubchunksThese codenames stand for refinement signals that fine-tune the quality estimate at a very granular level — individual subsections (subchunks) of a page. Their exact function is not fully documented in the available material. They are not a standalone main system but refine chard and NSR at the section level.
  • 11B/COriginalContentScoreThis score measures how much first-hand material a piece of content contains — information found only there, that an AI could not reconstruct from other sources. The higher the score, the more original the content. It is the closest machine equivalent to the E-E-A-T dimension 'Experience' (lived experience and direct observation).
  • 12AIS-Calibration (Rater/QRG)Not a live signal used daily in ranking — but the foundation on which all quality models are calibrated. The IS-Score (Information Satisfaction) summarizes how well a page meets a user's information need, rated by trained human raters. The QRG (Quality Rater Guidelines) are the public rulebook by which these raters judge.
  • 13BTopic-Embeddings (Focus/Radius)Google computes a kind of 'topic map' from the entire text content of a website (embedding — a mathematical vector representation of the topic space). siteFocusScore measures how sharply the site's topic field is defined; siteRadius measures how widely it scatters thematically. A small radius means: a tightly focused site. The system measures thematic consistency, not subject-matter competence.

02Deep Dives9

03Leak fields14

  • BsiteAuthorityAuthority distilled from quality_nsr, applied in Q*.Q* / NSR
  • BlowQualityLow-quality flag, converted from quality_nsr.NsrData.Q*
  • BpredictedDefaultNsrHistoricized baseline quality score (VersionedFloatSignal → the trajectory counts).NSR
  • BnsrConfidenceConfidence in its own NSR judgment (deprecated).NSR
  • BchardScoreContent-quality value per document, calibrated to rater judgments.chard
  • B/CchardVarianceDispersion/uncertainty of the chardScore (high = an uncertain judgment).chard
  • BcontentEffortLLM-estimated creation effort and depth of a page.contentEffort
  • B/COriginalContentScoreOriginality/first-hand-material degree — the closest machine Experience proxy.OCS
  • B/Ctofu / keto / RhubarbCodenames for refinement/delta signals at the subchunk level.tofu-Familie
  • BsiteEmbeddingsVector representation of the site's topic space.Topic-Embeddings
  • BsiteFocusScoreHow sharply outlined the site's topic field is.Topic-Embeddings
  • BsiteRadiusHow widely the site scatters in topic space (small = focused).Topic-Embeddings
  • AIS-ScoreInformation Satisfaction from rater judgments — the calibration norm.IS-Kalibrierung
  • B/CsiteQualityStddevStandard deviation of quality across a site (consistency).IS-Kalibrierung

04Theses1

Grouped by function class — the same five classes the catalogue filters by. A system belongs to exactly one; an article can touch two, and then it is listed under both.

All Deep Dives, grouped by topic