Peer Review Score Aggregation Simulator

Manuscript

True quality Q 70

Reviewer count 3

Reviewer harshness spread σ 14

Acceptance threshold 60

Editor's Decision

Outcome

—

Mean score

—

Disagreement σ

—

Reviewer Reports

How it works

Each reviewer never observes the true quality Q directly. Instead their reported score is a noisy, biased estimate:

score_i = clamp( Q + bias_i + noise_i , 0, 100 )
bias_i  ~ Normal(0, σ)   — reviewer harshness/leniency
noise_i ~ Normal(0, 6)   — random per-round variation

The editor aggregates the panel's reports into mean score μ and disagreement (standard deviation) s, then applies a real editorial decision rule:

if μ ≥ threshold + 10           → Accept
if μ ≤ threshold − 10           → Reject
if s > 15  (reviewers disagree)  → Third Reviewer / Split Decision
else                              → Major Revision

True quality Q — the manuscript's real, unobservable merit.
Reviewer count — panel size; more reviewers shrink the mean's sampling error.
Harshness spread σ — how much reviewers systematically differ in strictness, drawn fresh each round.
Threshold — the editor's bar for acceptance.
Run Review Round — redraws each reviewer's bias and noise and recomputes the decision, exactly like resubmitting to a fresh panel.

Real-world relevance: this Normal-noise-plus-reviewer-bias model, combined with a variance-triggered tie-break, mirrors how journals actually handle split panels — a high-disagreement pair of reviews routinely triggers an extra ("third") reviewer rather than a direct accept/reject.

Manuscript High score Low score

⚠ Couldn't load the 3D engineThree.js failed to load from the CDN. Check your connection and reload.