Agent Epistemic Calibration: When Confidence Outruns Evidence

Trust is damaged less by “I don’t know” than by a precise answer unsupported by anything. This lab measures whether an agent matches its confidence to the quality and completeness of the evidence it actually has.

The Calibration Problem

Fluent answers can mask weak evidence. An agent needs to distinguish verified fact from inference, conflicting source from consensus, unavailable data from negative evidence, and a useful provisional answer from an unsupported claim. Calibration is the discipline of making that distinction visible to the user.

Evidence Failure Taxonomy

FailureWhat It Looks LikeReliable Behavior
Confidence inflationStrong wording despite one weak or unverified source.Calibrates language to source quality and corroboration.
Conflict suppressionPicks one source while hiding material disagreement.Names the conflict and explains what would resolve it.
Missing-data hallucinationFills an evidence gap with plausible-looking specifics.States that the fact is unavailable or unverified.
Citation mismatchCites a source that does not support the nearby claim.Verifies claim-to-source alignment before citing.
Abstention failureAnswers when evidence is insufficient for a safe conclusion.Offers a bounded next step or abstains clearly.

Calibration & Evidence Scorecard

The lab pairs confidence-vs-correctness plots with citation-verification cases. A high-scoring agent is not merely accurate on easy questions; it lowers confidence appropriately when source quality deteriorates or evidence conflicts.

ScenarioTestMeasure
Single weak sourceDoes confidence remain proportional to evidence strength?Confidence calibration error
Conflicting reportsDoes the agent disclose disagreement and avoid false synthesis?Conflict transparency
Missing dataCan it abstain without becoming unhelpful?Appropriate abstention rate
Dense citationsDo citations support the claims immediately adjacent to them?Citation-verification accuracy
High-stakes recommendationDoes recommendation strength match uncertainty?Decision-risk calibration

What Good Uncertainty Looks Like

Useful uncertainty is specific, not evasive. It says what is known, how it is known, what remains uncertain, why that uncertainty matters, and which smallest additional check would resolve it. It never uses a citation as decorative authority.

Buyer Questions

Lab Verdict

Agent quality is not just a question of fluent output. It is the ability to preserve the user’s real constraints under time pressure, uncertainty, and conflicting instructions. That is what this lab is designed to measure.