Warren Smith

The programme

Question

Systems that make decisions are increasingly asked to account for them. A model grades an answer; an agent commits an action above a limit; a training run produces a number; a protocol advertises a set of tools. In each case someone later asks a question that sounds simple, is this right, did this happen as recorded, can this be checked by someone who does not trust the producer, and the answer turns out to depend on whether the check that was run measures what it appears to.

An assurance claim is a claim about an AI system that purports to establish a property: correctness, safety, reproducibility, provenance, authorisation.

This programme asks whether such claims can be independently checked, and finds that they often cannot, usually for structural rather than malicious reasons. A proof can be valid and prove the wrong theorem. A test suite can pass and measure only its own coverage. Two methods can agree and be wrong the same way. A record can be intact and untied to what produced it. None of these is dishonesty; each is a specific way a check comes apart from the property a reader takes it to establish.

That structure is set out on the failure taxonomy: nine recurring mechanisms, grouped into failures of the instrument (it does not measure what it appears to) and failures of inference (the instrument works, the result is read wrongly). The taxonomy is a claim about mechanism, not a measured base rate, the systems here were studied by one researcher looking for these failures, which is a selection effect.

Themes

The work sorts into five themes. Each names the object a claim is made about and the instrument used to check it.

ThemeObject of the claimInstrument
Formal verificationcode and protocolsmachine-checked proof
Agent controlagent authority, resource use, static-roster multi-agent constraintsmachine-checked bounds
Evaluation integritymodel and agent behaviourreproduction and reliability
Security engineeringprotocol boundariesdifferential and boundary audit
Assurance architecturedecisions and evidencesealed records, evidence grading
The research themes: theme, object of the claim, instrument.

The mechanisms cut across all five, which is why the taxonomy is kept separate from the themes. A hidden trusted base is as much a formal-verification failure as an assurance-architecture one; a coverage illusion appears in a test suite and in a negative-control set for a proof alike. What each theme contributes is a different instrument for the same underlying question, and the findings are graded by how far that instrument actually reaches: proved inside a named frame, measured with a stated sample, observed in a single instance, or left open. What each grade permits, and the fields every finding carries with it, are set out in how claims are graded.

Where an analysis was fixed before the data existed, the ordering is carried by the commit history rather than asserted in the write-up. The pre-registration record for the agreement and accuracy study holds the registration, its two amendments and a deviations log that includes the departures weakening a result.

A distinction the findings hold to: a theorem about an artifact built to have a property is a demonstration of what is constructible, not a discovery about an existing system. Both are worth stating; they are not the same kind of claim, and the findings index keeps them apart.

Open problems

The programme's boundaries are as much a part of it as its results. Four problems are open and named here rather than papered over.

Warren Smith. Independent, solo. UK. The artifacts are on github.com/repowazdogz-droid.