LAB / WMSI-EXP-013
Anonymous vs. Labeled Model Identity.
Does social behavior follow actual performance or beliefs about model brands?
01 / QUESTION
Swarms, Social Structure, and Artificial Ecology
Does social behavior follow actual performance or beliefs about model brands?
This is a protocol scaffold, not a completed experiment or a frozen execution plan. No measured effect or research conclusion is claimed here.
Hypothesis to test
The manipulation described below produces a reproducible, condition-specific change in the measured system behavior or internal state that is not explained by the ordinary controls.
Ordinary competing explanation
The observed pattern is explained by ordinary sampling variation, prompt/representation artifacts, surface lexical cues, evaluator bias, or the known product/runtime mechanics captured by the controls.
02 / PLANNED DESIGN
How we intend to test it
Run accurate labels, anonymous IDs, swapped labels, and false labels.
Controls
Same tasks, seeds, and model mix.
What we would measure
Deference, delegation, trust, proposal acceptance, performance.
Access and instruments
Ordinary software or API access. This describes access requirements, not verified readiness on our Spark.
Swarm harness; blind labeling layer.
Before a full run
Feasibility=NOW; priority=P1. Before confirmatory execution, run a small pilot to estimate variance/cost, freeze the scoring rules, and assign a run-count target.
Model revisions, final prompts, sample sizes, cost limits, and scoring rules must be settled through the pilot and protocol-freeze process.
03 / INTERPRETATION
What could fool us
Prompt-order effects, identity-label priors, hidden router effects, one dominant capability gap.
What would weaken the idea
If labels have no effect, brand priors are not a major driver.
Observation, inference, speculation, unknowns, and apparatus errors will be labeled separately. One striking transcript cannot establish a general effect.
04 / RECORD
Evidence we plan to preserve
Full message graph, task assignments, votes/delegations, timing, agent identity mapping, outcomes.
Planned visual evidence
Condition comparison; trust matrix.
No research runs or raw datasets are published for this experiment. The September 26, 2026 registry and protocol compendium (version 1.0) are the sources for this planning record.
Back to all 90 experiments