{"slug": "five-short-papers-on-making-ai-assisted-work-re-checkable", "title": "Five short papers on making AI-assisted work re-checkable", "summary": "A developer released five short papers on making AI-assisted work re-checkable, all archived on Zenodo with DOIs. The papers introduce concepts such as EMET, a byte-level integrity witness; BuildLang, a compiler with ambient capabilities; Witnessed Independence, which requires verifier independence; Proof Packets, which derive verdicts from checks; and Re-Perceived Effects, which replace actuator self-reports with re-perceived effects. The common thread is that verdicts should be re-derivable, state what they do not claim, and fail to UNVERIFIABLE rather than trust.", "body_md": "I have released five short papers on one idea: making AI-assisted work re-checkable. All five are archived on Zenodo with DOIs, and source and tests are public.\n\n-\n**EMET** — a byte-level integrity witness whose verdict {MATCH, DRIFT, UNVERIFIABLE} cannot, by construction, express \"trusted.\" Four implementations, 44 conformance vectors. [10.5281/zenodo.21230267](https://doi.org/10.5281/zenodo.21230267) · [source](https://github.com/HarperZ9/emet)\n-\n**BuildLang** — a compiler that puts ambient capabilities in the function type and seals re-derivable receipts verified by re-execution. [10.5281/zenodo.21231253](https://doi.org/10.5281/zenodo.21231253) · [source](https://github.com/HarperZ9/buildlang)\n-\n**Witnessed Independence** — records whether a verifier graded its own work, and refuses to decide when independence is not positively witnessed. [10.5281/zenodo.21232206](https://doi.org/10.5281/zenodo.21232206) · [source](https://github.com/HarperZ9/coherence-membrane)\n-\n**Proof Packets** — an envelope for one agent action whose verdict is derived from checks, so a claim can never vouch for itself. [10.5281/zenodo.21231837](https://doi.org/10.5281/zenodo.21231837)\n-\n**Re-Perceived Effects** — replaces an actuator's self-report with a re-perceived effect: on-disk hash against intended hash, return code, witnessed bytes. [10.5281/zenodo.21231747](https://doi.org/10.5281/zenodo.21231747)\n\nThe common thread: a verdict should be a re-derivable function of its inputs, should say plainly what it does *not* claim, and should fail to UNVERIFIABLE rather than to trust.\n\nMore at [harperz9.github.io](https://harperz9.github.io/).", "url": "https://wpnews.pro/news/five-short-papers-on-making-ai-assisted-work-re-checkable", "canonical_source": "https://dev.to/zaindanaharper/five-short-papers-on-making-ai-assisted-work-re-checkable-3n3n", "published_at": "2026-07-07 04:56:55+00:00", "updated_at": "2026-07-07 05:58:28.979058+00:00", "lang": "en", "topics": ["ai-safety", "ai-research", "developer-tools"], "entities": ["Zenodo", "EMET", "BuildLang", "Witnessed Independence", "Proof Packets", "Re-Perceived Effects", "HarperZ9"], "alternates": {"html": "https://wpnews.pro/news/five-short-papers-on-making-ai-assisted-work-re-checkable", "markdown": "https://wpnews.pro/news/five-short-papers-on-making-ai-assisted-work-re-checkable.md", "text": "https://wpnews.pro/news/five-short-papers-on-making-ai-assisted-work-re-checkable.txt", "jsonld": "https://wpnews.pro/news/five-short-papers-on-making-ai-assisted-work-re-checkable.jsonld"}}