Synthetic Players

Program

The five-phase experimental program

Sequential, sealed, and mechanically adjudicated — with each phase's question set by the previous phase's failure.

PhaseStatusQuestion and answer
Phases 1–2 — prototype and instrument repairSupersededThe historical v1 prototype and the mechanical re-adjudication layer built after it exposed analyst discretion.
Phase 3 — can an LLM serve as a behavioral subject?Sealed recordBare GPT-4.1 in repeated PD, framing, and RPS: 3 supported, 6 refuted, 1 inconclusive; X1 flips the corner.
Phase 4 — representation, counterfactuals, adversaries, driftSealed recordRegistry v3, 250 sealed arms, 2,864 runs: the S2 switch, label-swap conflict, corner-confounded δ-assays, adversary suite, and the sentinel that caught endpoint drift.
Phase 5 — the sixteen-persona panelSealed record16 sealed persona sentences × 6 conditions × 3 temperatures; 1,712 runs; both author predictions with teeth failed.
Phase 6 — the preregistered replication (not yet run)ProspectiveForbidden before publication by the scope seal; its design requirements are already written.

The through-line

Phase 1's prototype exposed analyst discretion → Phase 2 mechanized adjudication. Phase 3 found the bare subject at corners everywhere, with a paraphrase flip (X1) showing wording dominated the incentive manipulation → Phase 4 mapped representation: localized the flip to one sentence (X2/S2), decoupled labels from payoffs (D2), found δ-assays corner-confounded (E), and caught live endpoint drift with behavioral sentinels. Phase 5 asked whether cheap persona conditioning produces an interior, incentive-sensitive population — and answered with the composition result the paper reports. Phase 6 is the preregistered replication the scope seal deferred until after publication.

Scale and integrity

QuantityValue
Archived completed runs (all phases)5,505
Confirmatory replay contract4,916 runs (+3 legacy diagnostics = 4,919)
Round events / seat decisions54,276 / 108,552
Phase 4–5 ledger30,530 calls · 13,141,675 input tokens · 45,247 output tokens
Invalid trials in Phases 4–50 (24 provider-failure partials disclosed individually)
Registered author predictions refuted12
Process-failure instances publicly ledgered22