EXP-PERSONA-SWAP-R2

series member

Persona Swap Replication 2 — Generalizer Persona vs Position (rotation=2)

2026-03-14 L2 level paper3 1 runs $0.00

new

premortem

mock

real

metrics

analyze

review

krit

done

In plain language

Replication of the role-swap experiment with a different speaking order. If the generalizer is on top again — it is the thinking role, not the position.

What we found

UNDERPOWERED (N=1): No predictions scored

Predictions we made before running

0/2 confirmed

▶ Technical details

Research hypothesis

Replication of exp-persona-swap with rotation=2. Alpha gets generalizer persona, Zeta gets analytical. Tests whether persona effect (generalizer → highest TR) is robust across speaking positions. Baseline: exp-seed-sensitivity (N=16), Zeta(generalizer) mean TR=0.611. Original swap (rotation=0): Alpha(generalizer) TR=0.586.

Experimental setup

Type: simple

Condition	Parameters
SWAP	persona: SWAPPED, interaction: LIVE, n_agents: 6, n_rounds: 48, note: Alpha gets Zeta's generalizer persona, Zeta gets Alpha's analytical persona. Others unchanged.

Factors: persona_assignment (SWAPPED)

Parameters

n_agents: 6
n_rounds: 48
n_runs_per_condition: 1
model: gemini-2.5-flash-lite
temperature: 0.9
scheduler: round_robin

Trophic Ratios by Condition

Mean trophic ratio per agent across runs. Error bars = ±1 std dev. Higher TR = more upstream (exporter).