chard: Google's Page-Level Content Quality Model

01What is chard?

chard is Google's page-level content quality model. It rates the quality of individual pages. Human quality raters provide the calibration, and Google trains them on the Quality Rater Guidelines (QRG). The name 'chard' — a leafy green vegetable — follows Google's pattern of naming systems after foods, like 'tofu' and 'kale'.

The Google API leak reveals two chard fields: chardScores (the quality scores themselves) and chardVariance (a confidence measure that shows how certain the model is in its verdict). Together, they give a quality assessment and an indicator of how reliable that assessment is.

chard is designed to evaluate content quality, not link quality or user behavior. It assesses the text, structure, and substance of a page: whether the main content is helpful, whether supplementary content adds value, and whether the page shows the E-E-A-T signals described in the QRG.

02The calibration chain: IS-Calibration → chard → NSR

chard is fed by IS-Calibration (System 12), the human rater system that provides ground truth for quality models. So chard's quality scores ultimately derive from human judgments. Raters evaluate pages according to the QRG, and chard learns to predict what a rater would say about a new page.

chard feeds into NSR (System 7), the normalized site rank. This creates a three-level quality chain. IS-Calibration provides the ground truth (human judgments), chard produces page-level quality predictions, and NSR aggregates them into site-level quality scores. Each level transforms the signal: rater judgments become model predictions, and model predictions become site-level aggregates.

The chardVariance field is architecturally significant. A high variance score means the model is uncertain about its quality assessment. The page type may be unusual, the content ambiguous, or the page may not match the training data well. Downstream systems can use this uncertainty: NSR may weight high-variance chard scores less heavily, or flag them for additional rater review.

03YMYL: Your Money Your Life pages

chard matters most for YMYL (Your Money Your Life) pages, which could affect the user's health, financial stability, or safety. The QRG sets higher E-E-A-T standards for YMYL pages, and chard's calibration reflects this. A YMYL page must show more expertise, authoritativeness, and trustworthiness than a non-YMYL page to receive the same quality score.

YMYL classification is not binary but a spectrum. Medical information about treating a disease is clearly YMYL. A recipe for chocolate cake clearly is not. Financial tips, legal information, and news about current events fall in between, and chard must navigate that range.

The chard + YMYL combination creates a specific risk for publishers. Content that is technically accurate but lacks the E-E-A-T signals expected for its YMYL category will receive a lower chard score. A medical article written by a non-expert may be rated lower than one written by a board-certified physician, even if it is factually correct. The reason: the QRG instructs raters to evaluate the author's credentials for YMYL content.

04chard in the ranking architecture

chard operates at the document level (Reach: Doc). It produces quality scores for individual pages, not for entire sites. This distinguishes it architecturally from Panda (site-level) and Q* (site-level): chard evaluates each page on its own merits, while Panda and Q* aggregate across the site.

chard's E-E-A-T dimension mapping is Expertise (Exp: primary). The main signal chard contributes is whether the page demonstrates genuine expertise. The indirect Trust signal (T: indirect) follows from the fact that quality content is more trustworthy, but trust is not chard's primary function.

chard has no upstream dependencies beyond IS-Calibration (fedBy: [12]). That makes it a focused, single-source model: it takes rater calibration as input and produces page-level quality predictions. The simplicity of one input and one output is characteristic of quality models that need to be transparent and debuggable.

05Implications for SEO practitioners

chard's calibration chain means that content quality is ultimately defined by the QRG. The most effective SEO strategy for chard is to understand what the QRG describes as high-quality content and to produce content that meets those criteria, not to reverse-engineer the model.

The chardVariance field has an important implication: pages that are unusual or don't fit common patterns may receive high-variance scores. That is not inherently bad. It means the model is uncertain, not that the page is low quality. But unusual content may take longer to rank, because the system needs more data to assess it confidently.

For YMYL content, the QRG's emphasis on author credentials means that authorship signals matter. Bylines, author bios, and author pages that demonstrate expertise are not just good UX. They are signals that chard may use to assess whether the page meets YMYL E-E-A-T standards.

The Hoax detection component means that content that is factually incorrect or misleading will be penalized, even if it is well written. This matters most for news publishers: a well-written article that contains factual errors will receive a lower chard score than a less polished but factually accurate one.

06References