Transform text with AI — and carry a receipt for it.

Attest, don't detect. Paste a paragraph, reshape it with the sliders, and download a signed receipt anyone can verify offline — it proves what was transformed and by whom, with no SUM software needed to check it. Chain of custody for AI-transformed text.

0
1.00

Want the per-document readout — “what changed in my text”?

The receipts above attest that a transform happened and by whom. To see, claim by claim, what an AI rewrite kept, dropped, or added in your own document:

pip install "sum-engine[research,judge]"
sum meaning-diff source.txt rewrite.txt --scorer nli

A per-document measurement under a named judge — not a certified bound (a sum.meaning_risk_receipt.v1 over a corpus is the (1−δ) guarantee). Integrators verify any SUM receipt offline, dependency-light: pip install "sum-engine[verify]"python -m sum_verify. See the meaning-loss frontier.


Verify a bundle

Paste a SUM bundle JSON. This in-browser verifier runs two checks: structural — recomputes the state integer from the canonical tome and confirms it matches the claim; Ed25519 — if the bundle carries a public_signature and public_key, the signature is verified natively via SubtleCrypto (Chrome 113+, Firefox 129+, Safari 17+). No server, no network, no keys to supply. HMAC (shared-secret) signatures still require sum verify --signing-key ….