Prior-Estimate Anchoring

Problem

The second judgement is supposed to be independent, and it is not. A prior score included only as context metadata shifts the new rating toward its value: across 185,271 successful evaluations the shift reached a Cohen's d of 0.71, and 48% of the corrections the judge would otherwise have made were blocked, so a draft that scored low stayed low and one that scored high stayed high. The pull is not an artifact of weak models — a fourteen-model benchmark found frontier systems above 95% accuracy on the anchor-free control condition still moved, so control accuracy does not predict resistance to a plausible anchor. It is not confined to numbers either: a categorical prior analysis result shifts a code-vulnerability agent's call at 23.5% cross-model susceptibility, behind framing at 33.2% and ahead of the halo effect at 18.4%. Chain-of-thought does not remove the effect, and neither does an instruction to disregard the metadata. Agreement between stages therefore measures the strength of the pipeline's own bookkeeping rather than the quality of the artifact.

Solution

Separate the loop's bookkeeping from the judging context. The orchestrator retains the revision number, the attempt counter, and every prior score for convergence detection and logging, while the judging call receives only the artifact and the rubric — no field, header, or preamble naming a previous value, and no summary that implies one. Where a second opinion has to follow a first, run both judgements from independent contexts and combine them afterwards instead of nesting one inside the other. When prior state genuinely has to stay visible, blind or randomise it so it cannot act as a numeric target; the 6G control work replaces fixed heuristic anchors with a randomised draw for exactly this reason. Measure what is left with a paired experiment that re-scores the same artifacts with and without the metadata, and treat a disregard instruction as a note rather than a control, because the measured effect persists through it.

When to use

• Recognising this failure when a scoring, grading, or triage stage receives the previous score, attempt count, or earlier verdict in its context.
• Reviewing a refinement loop whose scores creep by one point per revision no matter how much the artifact changed.
• Auditing a second-opinion or escalation step that was sequenced after a first judgement it could read.
• Investigating why a judge names a defect in its written reasoning but does not move the score enough for the gate to act on it.