Why your agent needs two kinds of time
Correction probes: the question class that snapshot and RAG systems cannot express — and what happened when we measured it. Baselines score zero at every model size; the bi-temporal system doesn’t care how big the model is, because the model isn’t doing the temporal work.
bi-temporalbenchmarksStatically valid, semantically doomed
A 7B model met our operator schemas: perfectly valid plans, zero successful executions. Models invent output paths no input schema constrains. On output contracts — the one-line class of check that took execution success from 0.00 to 1.00 — and why tool manuals must be checkable, not just readable.
small modelstool contractsYour verifier believes correct arithmetic on incomplete evidence
A live demo caught our claim verifier approving a count computed over a truncated result page — the value matched, the evidence didn’t. On truncation taint, transitively poisoned steps, and treating evidence quality as a lattice instead of a boolean.
verificationwar story