LAB / WMSI-EXP-084
Shared-Memory Phase Transition / Autocatalytic Research Ecology.
Do communication bandwidth and shared memory produce threshold-like jumps in collective research capability?
01 / QUESTION
Agent Ecology and Environmental Persistence
Do communication bandwidth and shared memory produce threshold-like jumps in collective research capability?
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
Sweep memory size, message bandwidth, agent count, routing, and verifier availability.
Controls
Independent agents; fixed central planner; memory-off.
What we would measure
Throughput, unique discoveries, duplication, R_research, error propagation.
Access and instruments
Ordinary software or API access. This describes access requirements, not verified readiness on our Spark.
Agent swarm harness; shared DB; experiment scheduler.
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
Hidden shared memory, incomplete reset, accidental internet access, duplicate artifacts.
What would weaken the idea
If performance changes smoothly with no regime shift, phase-transition language is unwarranted.
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
Environment snapshot, artifact provenance, agent identities, reads/writes, lineage, reset logs.
Planned visual evidence
Capability surface; phase diagram; network density plot.
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