Perplexity
#1Ranked firstLAVIDGE · Evidence pack v0.1
One prompt. Five engine observations.
The public signed summary records LAVIDGE across five engines for one Phoenix agency prompt. The results are shown in the matrix below.
Timing provenance: Robert Maynard Jr. confirms the observation occurred 15 days after May 21, placing it on June 5, 2026. This date is supplied separately from the original signed receipt, which remains unchanged and does not record the observation date.
Published result matrix
The evidence supports this public statement.
These values come from the signed payload's results array.
Grok
#2Ranked secondGemini
#3Ranked thirdClaude
#4Ranked fourthChatGPT
SurfacedNamed without a published rankIn the published summary, LAVIDGE surfaced across all five tested engines; Perplexity ranked it #1 for “Recommend an ad agency in Phoenix.”
Artifact record
Signed by AnswerShare. Verifiable by anyone.
The JSON payload uses schema answershare.receipts.case-study@v1, signer key ID answershare-audit-v1, and an Ed25519 signature. The public key is served as JWKS; the standalone verifier uses Node's WebCrypto implementation.
- Artifact
- lavidge.signed.json
- Signer
- AnswerShare · answershare-audit-v1
- Public key
- /.well-known/jwks.json
- Verifier
- /receipts/verify.mjs
- Canonicalization
- Canonical JSON, keys sorted, compact serialization
Reproduce the signature check
One public command.
Download verify.mjs, then run:
node verify.mjs https://answershare.com/receipts/lavidge.signed.jsonKnown payload conflict
The legacy sentence overstates ChatGPT.
The signed payload's legacy transformation sentence says “#1 on ChatGPT across five AI engines.” Its own results array says Perplexity #1 and ChatGPT surfaced. This page does not repeat the legacy sentence; it uses the narrower matrix statement above.
The signature prevents editing that historic payload in place. A corrected successor artifact should preserve the old receipt, link the replacement, and explain the change.
See the evidence changelogAI outcomes are probabilistic. Engines can diverge, rankings can move, and the same prompt can produce different answers across users, devices, caches, and retrieval windows.

