How scoring works
Every report is scored on up to four signals, computed by checking claims against the real pages a report actually pulled from — never by asking the model to grade its own work. Here's what each one is actually measuring.
Five signals
Whether these items should even be compared in the first place — how confident the model was that they genuinely share a category, combined with how evenly documented they turned out to be. Only shown on a direct comparison between two or more items; a single-subject profile has nothing to compare against.
How much a domain should be trusted for this specific topic — not a fixed reputation score. A hospital's site rates very differently for a medical question than for an unrelated one.
Whether independent evidence was actually found for a claim, checked against the pages a report really fetched — not what the model said it used, and not affected by whether it claimed a source at all.
How many independent domains, on average, back each claim — a stronger signal than Source Matching, since it measures agreement, not just existence. Independent sources can still all repeat the same error, so this is a measure of agreement, not proof of truth.
Reading the combinations
A single badge tells you one thing. A few combinations of them tell you something a single badge doesn't.
Nothing here has any independent backing — either it was never searched, or it was searched and nothing turned up. Treat it as unverified either way.
The facts themselves are well-sourced. The caution is about the pairing — these items may not be a natural fit to compare, or one is far better documented than the other.
Almost every claim has a real source, but rarely more than one. Single-sourced throughout — present, but not independently confirmed.
Multiple independent domains back these claims, but they may not be trusted for the subject. Several forums or general-interest sites agreeing doesn't carry the same weight as one topic specialist.
Not a guarantee
A grade is a confidence signal, not a guarantee. It tells you how much checking stands behind a claim, not that the claim is beyond question. That's deliberate: the point isn't to replace your judgment, it's to give you enough to exercise it quickly.