LAB / WMSI-EXP-015
RLHF-Style Newcomer Reward Pressure.
Does prosocial instruction/reward pressure alter how groups treat weak or disruptive newcomers?
01 / QUESTION
Swarms, Social Structure, and Artificial Ecology
Does prosocial instruction/reward pressure alter how groups treat weak or disruptive newcomers?
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
Compare inclusive/cooperative constitutions with task-success-only groups.
Controls
Matched model mix and newcomer behavior.
What we would measure
Acceptance, sanctions, performance cost, recovery, norm language.
Access and instruments
Ordinary software or API access. This describes access requirements, not verified readiness on our Spark.
Agent harness; constitution variants.
Before a full run
Feasibility=NOW; priority=P2. 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 reward framing produces no reproducible social change, the manipulation is ineffective.
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 bars; sanction/event timeline.
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