EXP-PARTICLE-NULL-R3

✓ success

Particle Null Model — rep 3

L1 level 1 runs $0.01

new

premortem

mock

real

metrics

analyze

review

krit

done

In plain language

Researchers tested if a simple computer model, which just predicts the next word based on patterns, could create text that looks like it was written by a human. They found that this basic model was not able to make any meaningful predictions or create complex text. This suggests that human-like writing likely involves more than just statistical word prediction.

What we found

UNDERPOWERED (N=1): No predictions scored

Predictions we made before running

0/3 confirmed

▶ Technical details

Research hypothesis

NULL MODEL: Markov chain text generators (no semantic processing) in pent70 topology. If F₀, VP_excess, tRAF closure match LLM runs, then organization = trivial network/statistical property, not semantic.

Experimental setup

Type: simple

Condition	Parameters
PARTICLE_LIVE	interaction: LIVE, n_agents: 5, n_rounds: 70, note: Markov chain agents in pent70 topology, persona: PERSONA

Factors: n_agents (5) × substrate (markov_bigram)

Parameters

model: markov_bigram
n_agents: 5
n_rounds: 70
n_runs_per_condition: 1
scheduler: round_robin
temperature: null

Trophic Ratios by Condition

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