IDKMesh

Adaptive Verification Ecology (AVE)

Status: experimental algorithm proposal + simulator target
Date: 2026-09-22
Scope: routing, verifier allocation, generation backpressure, and diversity preservation for the Verified Swarm Runner / Connector Control Plane.

1. Why this exists

IDKMesh already has useful nature-inspired mechanisms:

The missing piece is a single closed-loop trust policy that joins those ideas around the product’s strongest question:

How should IDKMesh allocate workers and verifiers when generation is cheap, verification is scarce, and nominal reviewer count can badly overstate independent evidence?

AVE is a proposed answer. It is deliberately not a biological simulation and not a claim that software projects are organisms or markets. Biology, ecology, economics, and physics supply candidate control mechanisms. The mechanism stays only if it beats simpler baselines under matched budgets.

2. High-level loop

WorkUnit
  |
  v
policy/risk feasibility filter
  |
  v
niche-aware worker routing
  |     |    -- entropy/temperature preserves exploration
  |    -- family occupancy penalizes monoculture
  |    -- shadow prices penalize scarce review/compute
  v
untrusted candidate
  |
  v
danger / uncertainty estimate
  |
  v
immune-style verifier portfolio
  |     |    -- known-bad probes maintain detector memory
  |    -- correlation penalty favors independent families
  |    -- risk-adaptive quorum/fan-out
  v
VerificationResult + evidence
  |
  +--> update worker evidence
  +--> update verifier evidence
  +--> update queue shadow prices
  +--> update concentration/diversity state
  |
  v
human/governance integration remains outside AVE

AVE is a recommendation and resource-allocation layer. It does not grant permissions, decide truth without verification, or merge.

3. Scientific inspirations and exact IDKMesh mappings

3.1 Adaptive immunity -> verifier memory and anomaly response

Useful engineering inspirations:

IDKMesh mapping:

Immune concept AVE object
antigen candidate artifact / known-bad probe
detector verifier / validator
memory verifier reliability posterior and breach history
immune diversity verifier-family diversity
danger signal risk + uncertainty + provenance anomaly + correlated-worker signal
tolerance low-risk, well-characterized work uses minimal sufficient verification
immune overreaction unnecessary verification cost / false rejection
immune escape defect accepted by all selected verifiers

Important boundary: “danger theory” is used only as an engineering analogy for combining contextual anomaly signals. It is not required as a biological claim.

3.2 Ecology -> niches, carrying capacity, and anti-monoculture

Ecological coexistence work emphasizes that stable diversity depends on differences in niches/resource use; biodiversity can sometimes provide resilience when components respond differently to disturbances.

IDKMesh mapping:

The goal is not diversity for its own sake. Diversity is valuable only when it reduces correlated failure or covers a capability niche.

3.3 Economics -> shadow prices for scarce verification capacity

A verifier queue is a congestion problem.

Instead of a token or cryptocurrency, AVE uses an internal shadow price for scarce resources.

For resource r:

lambda_r(t+1) =
  clip(
    lambda_r(t)
    + eta_r * (utilization_r(t) - target_r),
    0,
    lambda_max
  )

When review demand exceeds sustainable capacity:

When capacity recovers, the price falls.

This is inspired by network-utility/congestion-control work using feedback and shadow prices. It is not money and creates no transferable asset.

3.4 Statistical physics -> entropy-regularized exploration

A fixed exploration rate is brittle. AVE uses a temperature-controlled distribution.

For eligible worker a and task j, define an adjusted utility U(a,j).

P(a -> j) =
  exp(U(a,j) / T)
  -----------------------------
  sum_k exp(U(a,k) / T)

Interpretation:

A first feedback rule can be:

T(t) = clip(
  T_base
  + k_u * mean_route_uncertainty
  + k_s * stagnation_signal
  - k_q * lambda_review,
  T_min,
  T_max
)

This is a practical use of the “free-energy” idea already discussed in SCIENTIFIC_FOUNDATIONS.md: quality pressure plus a controlled diversity/entropy term.

3.5 Bayesian/bandit learning -> learn task-family fit without freezing newcomers out

For each worker family f and task class c, maintain a posterior over verified success.

A simple Beta-Bernoulli starting point:

theta_(f,c) ~ Beta(alpha_(f,c), beta_(f,c))

A router can sample theta (Thompson-style) or use posterior mean + uncertainty.

Updates must use retained verification/outcome evidence, not raw activity volume.

This makes the routing question:

Which worker family should be tried for this task class, given observed verified outcomes and uncertainty?

rather than:

Which provider has the biggest model?

3.6 Quality-Diversity -> preserve proven specialists, not one global winner

MAP-Elites is useful as a model for an archive indexed by meaningful behavioral descriptors.

A future AVE archive can index candidate worker/verifier strategies by dimensions such as:

Each cell retains one or a few high-performing verified configurations.

This prevents a globally strong provider from erasing specialized combinations that are better for a minority of tasks.

4. Core AVE state

4.1 WorkUnit state

For WorkUnit w:

4.2 Worker state

For worker/agent a:

4.3 Verifier state

For verifier v:

4.4 Global control state

5. Routing objective

After the hard policy/permission filter, a first worker-task utility is:

U_worker(a,w) =
    Value(w)
  * Capability(a,w)
  * SampledReliability(a, class(w))
  * IndependenceBonus(a,w)
  * NicheBonus(a,w)
  / (
      1
      + lambda_review * ExpectedReviewCost(a,w)
      + lambda_compute * ExpectedComputeCost(a,w)
      + RiskFriction(a,w)
    )

Terms:

The final choice is entropy-regularized, not deterministic greedy selection.

6. Ecological occupancy rule

Let n_(f,c) be active attempts by worker family f in task class c.

A simple negative-frequency term is:

NicheBonus(f,c) =
  1 / (1 + n_(f,c))^gamma

Add a global family-share cap:

share_f <= K_f(risk_class)

unless no feasible alternative exists.

For high-risk work, the allowed concentration can be stricter.

This is not a fairness score or contributor worth score. It is a correlated-failure control.

7. Immune-style verifier allocation

7.1 Known-bad probes

IDKMesh already has seeded known-bad candidate logic in the gate-audit direction.

AVE makes this an online control input.

For verifier v:

probe_reliability_v ~ Beta(a_v, b_v)

On a known-bad probe:

A verifier that repeatedly accepts known-bad probes is not silently trusted because of nominal status.

7.2 Danger score

A first bounded score:

D(w,candidate) =
    q_r * Risk(w)
  + q_u * RouteUncertainty(worker, w)
  + q_n * Novelty(w, candidate)
  + q_p * ProvenanceAnomaly(candidate)
  + q_c * CorrelatedWorkerPressure(w)
  + q_h * HistoricalEscapeRate(task_class)

D maps to a minimum verifier budget.

Example policy:

D < 0.30       -> minimum 1 verifier
0.30 <= D<0.65 -> minimum 2 verifier families
D >= 0.65      -> minimum 3 verifier families + human checkpoint if policy requires

The exact thresholds are experimental.

7.3 Verifier portfolio selection

Select verifiers greedily or through a small combinatorial optimizer to maximize:

VerifierValue(S) =
    ExpectedDetection(S)
  + Diversity(S)
  + Coverage(S)
  - lambda_review * Cost(S)
  - CorrelationPenalty(S)

subject to:

This is the component most directly tied to E017: N verifiers are useful only if their joint evidence is stronger than one verifier’s evidence.

8. Risk-adaptive quorum

Do not use one permanent majority rule.

For a verifier portfolio S, the aggregation rule should depend on:

E017 showed that for the measured one-sided partial-test panel, majority was a poor rule and unanimity-to-accept substantially reduced errors. That result must not be generalized to arbitrary two-sided verifiers.

AVE therefore treats quorum as a policy selected from evidence, not a constant.

9. Economic generation backpressure

Generation should slow when verification cannot keep up.

Let:

rho_verify =
  arriving_verification_work /
  effective_verification_capacity

When rho_verify > 1 persistently:

This is preferable to producing an ever-growing queue of untrusted candidates.

10. Product integration points

Connector Control Plane

Add optional policy hooks, not vendor-specific logic:

route(work_unit, eligible_connectors, evidence_state) -> RouteDecision
select_verifiers(candidate, evaluator_requirements, evidence_state) -> VerificationPlan
update(outcome) -> EvidenceStateDelta

The connector kernel still owns:

AVE consumes normalized connector metadata and produces recommendations.

WorkUnit

Use existing fields where possible. Do not add new schema fields until an implementation proves they are necessary.

Potential future fields/extensions:

EvaluatorPlan

AVE should generate or help select an EvaluatorPlan, but the plan remains verifier-owned and content-bound.

A router must not weaken:

gate-audit

The current gate-audit surface can become the first measurement input for AVE:

gate-audit output
 -> measured verifier correlation
 -> effective panel size / breach evidence
 -> AVE verifier-family state
 -> future verifier allocation

This creates a clean product progression from today’s tool to the future control plane.

GUI

Show the control state directly:

11. First synthetic experiment

Compare under equal workloads and seeds:

  1. capability-static
    • greedy capability routing;
    • one fixed verifier;
    • no memory;
    • no backpressure.
  2. diversity-static
    • same workload;
    • family-concentration penalty;
    • fixed two-family verifier allocation;
    • no learning/backpressure.
  3. AVE
    • posterior routing;
    • niche penalty;
    • entropy temperature;
    • known-bad probe memory;
    • correlation-aware verifier portfolio;
    • shadow-price backpressure;
    • risk-adaptive verification.

Environment controls

Sweep:

Metrics

Report a Pareto vector, not one permanent score:

12. Falsification criteria

AVE should be rejected or simplified if, under matched budgets:

A successful result is a reproducible Pareto improvement, not merely a more complex algorithm.

13. Development slices

AVE-0 — simulator and ablations

AVE-1 — measurement adapters

AVE-2 — dry-run router

AVE-3 — verifier-plan recommender

AVE-4 — bounded live cohort

AVE-5 — feedback activation

Only after the cohort shows benefit:

14. Safety and governance boundaries

AVE MUST NOT:

Every policy update must be inspectable and replayable.

15. Research references

Primary external inspirations:

Repository evidence and foundations:

16. Design refinement after first ablation

The first cumulative matched-budget ablation adds an important caution to the original AVE proposal.

The strongest synthetic safety effect currently comes from verifier-family diversity. In contrast, using known-bad probes as a positive verifier-ranking signal is not yet justified: when probe coverage is unrepresentative, posterior updates can steer selection toward a misleading estimate of real verification quality.

Therefore the next candidate policy for product dry-run is deliberately smaller:

AVE-core =
  ecological task anti-monoculture
  + posterior task-family learning
  + bounded entropy exploration
  + verifier-family diversity
  + risk-adaptive verifier floor/quorum
  + verification shadow-price backpressure
  + price-aware routing

Known-bad probes remain valuable, but for now their supported roles are:

They should not yet create positive production trust or automatically promote a verifier.

The targeted experiment is:

It compares:

  1. verifier-family diversity alone;
  2. diversity + risk adaptation with no probe memory;
  3. ave-core;
  4. the original full AVE including probe memory.

This is a design correction, not a claim that immune-style memory is useless. The claim under test is narrower: probe-derived routing trust must be earned by representative-outcome evidence rather than assumed from synthetic probe success.