EXP-PERSONA-FREE-SCARCITY

◐ partial

Persona-Free Scarcity — Crystal Ceiling Crucial Test

2026-04-13 L3 level paper3 9 runs $0.36

new

premortem

mock

real

metrics

analyze

review

krit

done

In plain language

Does hierarchy emerge from scarcity alone, without designed persona differentiation?

▶ Technical details

Research hypothesis

Crucial test: scarcity + identical agents (no personas). If emergent structure appears → first result not attributable to designed differentiation. If not → crystal ceiling is persona-dependent. Three conditions: SCARCE_PERSONA (budget + personas), SCARCE_IDENTICAL (budget + identical), UNLIMITED_IDENTICAL (no budget + identical, control). P1: SCARCE_PERSONA VP_rate > UNLIMITED_IDENTICAL VP_rate (confirms scarcity effect with personas). P2: SCARCE_IDENTICAL VP_rate > UNLIMITED_IDENTICAL VP_rate (crucial: scarcity alone creates structure). P3: SCARCE_PERSONA VP_rate > SCARCE_IDENTICAL VP_rate (personas amplify scarcity effect).

Experimental setup

Type: multi_condition

Condition	Parameters
SCARCE_PERSONA	label: Budget 250 + personas, interaction: LIVE, persona: PERSONA, n_runs: 3
SCARCE_IDENTICAL	label: Budget 250 + identical agents, interaction: LIVE, persona: IDENTICAL, n_runs: 3
UNLIMITED_IDENTICAL	label: No budget + identical agents (control), interaction: LIVE, persona: IDENTICAL, n_runs: 3

Parameters

n_agents: 5
n_rounds: 30
model: anthropic/claude-haiku-4-5
temperature: 0.9

Trophic Ratios by Condition

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

scarcity persona-free crucial-test life-roadmap crystal-ceiling