Synthetic Players
Paper PDF

Review round

Round 11 — Explore Science review of v12

v12 → v13 · 96/100, Platinum

Explore Science (external) · 2026-07-31 · 96/100, Platinum · manuscript arc: v12 → v13

Archived record

Eight minors, all adopted or strengthened for v13: a global-multiplicity limitation (no study-wide alpha allocation across the registered predicates), provider-failure accounting in the main text, the P5-2 prompt-cluster bootstrap and Dirichlet–Jeffreys dependence sensitivities, interval-bearing Figure 3, and ρ=.75 identified explicitly as a preregistered heuristic.

Linked in the research graph

Everything connected to this item, in both directions.

Claims

Analysiss

  • P5-2 dependence audit (v13)Post-adjudicationPrompt-cluster bootstrap [0.071, 0.189] and fixed-panel Dirichlet–Jeffreys [0.152, 0.195] around the 0.128 point.

Manuscript versions

  • v13 — dependence-aware candidateSupersededAdds the global-multiplicity limitation, provider-failure accounting, P5-2 prompt-cluster bootstrap and Dirichlet–Jeffreys sensitivities, and interval-bearing Figure 3.
  • v12 — near-arXiv preprintSupersededExtends the replay perimeter to all of Phase 3 (320 runs + 20 baselines), adds the independent bootstrap-coincidence audit, full leaning-strata table, matched-lattice entropy reanalysis, and decoding audit; the abstract leads with the latent-propensity posterior.