/proof › RR-001 scoreboard › H9
Hypothesis H9
WordingPer-domain marginal cost stays under $10/day
Falsification threshold
Mean daily spend exceeds $10/day over the 30 daysCurrent statuspending
Evidence summaryAwaiting evaluator run
Pre-disclosed expected outcome (honesty disclosure):
Expected supported — per-tenant cost cap enforced architecturally at lib/llm/costCap.ts.
Expected supported — per-tenant cost cap enforced architecturally at lib/llm/costCap.ts.
How this hypothesis resolves
The threshold above is the pre-registered falsification rule. Once the evaluator runs (per the schedule in the protocol document), the `currentStatus` column on `reference_run_hypotheses` updates and this page reflects the verdict. All evaluator runs are cryptographically sealed via the daily Merkle anchor.
Source of truth
- Schema:
reference_run_hypotheses(migration 0104) - Evaluator:
lib/referenceRun/hypothesisEvaluator.ts - Writer:
DrizzleHypothesisDbWriterinlib/referenceRun/dbWriters.ts - Locked wording:
LOCKED_HYPOTHESESinlib/referenceRun/hypothesisEvaluator.ts