← back to timeline

EXP-CROSS-SUBSTRATE-SINGLE-ENTITY-DOMINANCE-PROBE

… pending

Cross Substrate Single Entity Dominance Probe

2026-05-27 L4-L5 level 0
new
premortem
mock
real
metrics
analyze
review
krit
done

In plain language

This experiment investigates whether different types of systems naturally tend to have one dominant entity, even when starting with multiple entities. Researchers are checking if this "single-entity dominance" happens across various system types unless specific measures are taken to prevent it. The results are still being analyzed to see if this tendency is confirmed.

▶ Technical details

Research hypothesis

Three findings from DIFFERENT substrate classes converge on single-entity-dominance. Hypothesis: substrate-class-INVARIANT property (SED-default) — every substrate >N=1 trends toward single-entity-dominance unless an anti-collapse mechanism is engineered.

EXPLICIT SCOPE RESTRICTION: NOT a SAS-vs-MAS reasoning claim. Substantively distinct: substrate-default-collapse-shape, NOT compute-accounting bound.

Pre-registered threshold: modal-entity-dominance-share ≥ 70% per cell, ≥4/5 cells agree on classification under ≥2/3 operationalizations → CONFIRMED.

construct paper3-related paper6-related paper7-related pool-drained phase7-3-generated cross-substrate engine-bash-retro