Skip to content

Capability Claims: Evidence with an Expiry

Two Outcomes report successful work and the same favorable verdict. One came from a constrained local Environment with a large sample, low cost, and an expiry next month; the other used different tools, fewer Cases, higher cost, and a shorter evidence window. Their shared verdict—or one impressive number—cannot choose a universal winner. The useful result is an exact statement of what each subject revision demonstrated under named conditions.

Capability claims are Designed; no claim or routing path runs. State of Work records maturity; ADR 34 owns the claim law.

Shape the supported claim

A claim derives only from a healthy, version-pinned TrialSuite@1 and its retained Outcomes. This page defines no health algorithm. The evidence must survive its declared controls, harness and Evaluator health, leakage checks, calibration review, and required receipts.

Make the claim precise enough for a consumer to decide whether its evidence applies. Pin the exact Animator, model, adapter, toolset, and configuration revisions; name the task class, Cases, Rubric, Evaluators, and Environment. Retain sample count, controls, verdict distribution, uncertainty, and noise, so a favorable verdict does not hide how often it held. Record cost and latency per admitted success, counting failed attempts too. Creation time, expiry, and evidence references delimit how long and from what material the claim draws support.

Accuracy, latency, VRAM, cost, restraint, and tool behavior remain separate axes. The consumer decides which dimensions matter for its present request. Drift does not collapse them into one scalar.

Expire without rewriting history

A claim can guide current decisions only while its evidence is present, healthy, and unexpired. Changing the subject, toolset, configuration, Rubric, Evaluator, or Environment requires new Outcomes and a new claim. A silent refresh would borrow a conclusion from conditions no longer being tested. Keep the stale claim as historical evidence, without allowing it to steer current decisions.

Later loss, leakage, changes in Evaluator behavior, or contradiction invalidates only claims whose complete support closure has broken. Independently supported claims remain intact. Recovery means a new bounded trial and a new claim, while causal uncertainty can move through Returning findings.

Let each consumer decide

Suppose an application needs a minimum OCR accuracy in Slovak. In the designed qualification path, the requesting owner fixes the criterion, threshold, applicable evidence, and freshness. A candidate lacking that evidence is ineligible, even when its engine is warm. The receiving owner decides whether an exact claim satisfies the requirement.

A separate, optional ranking can compare fresh admitted claims among candidates that already meet those requirements and Ward, compatibility, availability, privacy, and authority checks. When optional ranking evidence is missing, Dispatcher uses its deterministic readiness order. It selects one candidate, issues the lease, and never retries another candidate merely because the first failed. Evaluation-driven qualification and ranking remain Designed.

For Toll, retained cost and latency evidence may inform spending policy. It neither authorizes payment nor supplies a budget, signature, or settlement. A cheaper local success can be relevant without making all Portal use wasteful.

Soulforge may compare baseline evidence, sealed-holdout Outcomes, expected change, and regressions for a frozen candidate. Passing Drift establishes eligibility only. The candidate handoff keeps that eligibility separate from the externally owned Promotion Decision; a claim cannot admit corpus, register a candidate, promote, route, or grant capability.

A capability claim remains what its evidence can carry: versioned, scoped, expiring, and useful only inside the consuming owner's decision.