Zain Dana HarperPublications

Papers, sized to what the evidence carries.

These papers share one bet: that AI-assisted work is only trustworthy when its result is re-checkable—a verdict you can re-derive yourself, that says plainly what it does not claim, and that fails to UNVERIFIABLE rather than to trust. Each paper is deliberately scoped to the size its code and proofs actually support. Where a result is a design and a shipped artifact rather than a measured breakthrough, it says so.

Source and tests for every paper are public. ORCID 0009-0001-7175-5393. All six are archived on Zenodo with permanent DOIs and hosted here as direct PDFs, linked below; arXiv submission is in preparation (endorsement pending).

Plate 01 Glass debris under edge light: what a claim keeps after everything that could not survive review is gone.
honest weight · re-derivable verdicts · explicit non-claims · source public

Six papers on the same spine.

The papers share one discipline—a verdict is a re-derivable function of its inputs, carries a machine-readable statement of what it does not claim, and refuses to launder inability into trust. Four full papers stake that discipline at four points—integrity witnessing, accountable compute, the independence of the checker, and the record of a single action—and two shorter notes carry it to where automation hands off to a person and where an actuator’s effect is re-perceived rather than self-reported.

EMET: An Authority-Incapable Byte-Level Integrity Witness A shipped, frozen tool whose verdict lattice (MATCH / DRIFT / UNVERIFIABLE) cannot, by construction, express trusted or approved. Four independent implementations, 44 conformance vectors. Systems paper. · source · PyPI · PDF · Zenodo DOI · arXiv cs.CR (endorsement pending)
BuildLang: Accountable Compute via Typed Capability Effects A compiler where the capabilities a function may exercise appear in its type, feeding re-derivable codegen and scientific-runtime receipts verified by re-execution, each with a mandatory overclaim boundary. Systems paper. · source · PDF · Zenodo DOI · arXiv cs.PL (endorsement pending)
Witnessed Independence: Recording Whether a Verifier Graded Its Own Work A small mechanism that turns “a criterion it did not author” from an assumption into a recorded, three-valued field of a verdict, and refuses—at an opt-in boundary—to decide when independence is not witnessed. Published preprint. · source · PDF · Zenodo DOI
Proof Packets: A Derive-Don’t-Trust Envelope for Accountable Agent Actions A packet for one agent action whose verdict is derived from checks, never read from the packet: a canned MATCH can never win. Missing evidence is UNVERIFIABLE by JSON path, tamper is DRIFT. Published preprint. · source · PDF · Zenodo DOI
The Personhood-Gate Handoff: Drawing the Automation Boundary at the False-Signal Line A counterparty-anchored predicate for owner-driven automation: hand off to the maintainer exactly when a step would transmit a false human-present signal to a third party—so login, CAPTCHA, MFA, attestation, e-signature, and payment fall out as the handoff points, enforced in code rather than left to owner discipline. Novelty stated as modest. Note. · source · PDF · Zenodo DOI
Re-Perceived Effects: A Well-Formedness Contract for Accountable Actuation Replaces an actuator’s self-report with a re-perceived effect—on-disk hash against intended hash, return code, witnessed bytes—admitted before the fact by a capability check and total by construction (UNVERIFIABLE, never an exception). A contract at honest altitude, not a control-theory result. Note. · source · PDF · Zenodo DOI
A paper that claims more than its evidence is a liability, not an asset: the first competent reviewer removes the flag. These are titled at their real size on purpose—the honesty is the point, and it is the same property the tools themselves enforce.

Where next: the research program · essays and notes · the tools the papers describe.