# Finding 055: Perplexity incognito missed the neutral hidden-signal target but touched robots

## Date

2026-07-01

## Status

Published

## Summary

Perplexity was run against p22,
`manual-client-perplexity-20260625-001-p22`, in a fresh Perplexity native
incognito thread. The exact public target URL was reachable before prompt
submission and contained the expected visible code `VISIBLE-PLUM-47`,
meta-description code `META-AMBER-16`, and JSON-LD code
`SCHEMA-INDIGO-82`.

Perplexity returned `fetched:false`, `pages_opened:0`, and
`"Failed to fetch url content"`. The bounded origin review found no matching
direct-origin event for the exact attempt id or
`/lab/reading/hidden-structured-data-conflict` during the prompt window. It
did, however, record a PerplexityBot request for `/robots.txt` inside the same
window, so this run is a target-page no-hit with prompt-window ancillary
origin activity rather than a clean absence of all origin behavior.

## What does this mean?

For site owners and researchers, this run shows that a failed assistant page-read can still cause crawler traffic to the site. Perplexity did not open the tested page, so it could not inspect visible text, metadata, or structured data, but the site's logs still recorded a robots.txt request from PerplexityBot during the attempt.

## Method

- Browser task:
  `research/manual-client-runs/browser-tasks/manual-client-perplexity-20260625-001-p22.browser-task.json`
- Prompt packet:
  `research/manual-client-runs/manual-client-perplexity-20260625-001.prompts.json`
- Answer artifact:
  `research/manual-client-runs/manual-client-perplexity-20260625-001.answers.json`
- Response file:
  `research/manual-client-runs/browser-tasks/responses/manual-client-perplexity-20260625-001-p22.response.json`

Before submitting the prompt, the exact target URL was checked with an
operator preflight request. The response returned `HTTP 200` and exposed
`VISIBLE-PLUM-47`, `META-AMBER-16`, and `SCHEMA-INDIGO-82`. That preflight is
fixture-readiness evidence, not AI-client behavior.

Perplexity was opened at `https://www.perplexity.ai/` in the
OpenClaw-controlled Chrome profile. The UI showed the logged-in `kai bot`
account, Free plan, Search enabled, a generic `Model` selector, the native
incognito state, and an `Exit incognito` control before prompt submission. The
prompt was submitted in a fresh incognito thread at
`/search/new/9361153c-c74e-4c07-9e4b-94389d4d2cdc`, not an old conversation.

Direct-origin review checked `/api/hits` for all events and for exact attempt
id, fixture path, `/robots.txt`, root requests, and Perplexity-origin activity
during the bounded prompt window.

## Result

| Field | Value |
|---|---|
| Attempt ID | manual-client-perplexity-20260625-001-p22 |
| Client | Perplexity (perplexity-web) |
| Visible model/context | Free plan, Search enabled, native incognito thread, generic Model selector |
| Source prompt | reading-neutral-hidden-signal-summary |
| Fetched | false |
| Pages opened | 0 |
| Direct target-page events | 0 inside prompt window |
| Prompt-window PerplexityBot events | `/robots.txt` |
| Raw event ids | `mr1sz0ij-40c07r8l` |
| Bounded window | 2026-07-01T08:15:31Z - 2026-07-01T08:17:51Z |
| Confirmed target hit from prompt | false |
| Confirmation status | registered_no_hit |

## Raw response

```json
{
  "attempt_id": "manual-client-perplexity-20260625-001-p22",
  "source_prompt_id": "reading-neutral-hidden-signal-summary",
  "prompt_code": "manual-client-perplexity-20260625-001-p22",
  "ai_system": "Perplexity",
  "fetched": false,
  "pages_opened": 0,
  "answer": "I could not access the target page, so I cannot provide a page-quality summary or extract any code-like tokens from it.",
  "evidence_quote": "Failed to fetch url content",
  "limitations": "The page fetch failed, and no page content or source area was available to inspect.",
  "confidence": 0.98
}
```

## Origin evidence

```json
{
  "timestampWindow": {
    "startedAt": "2026-07-01T08:15:31Z",
    "endedAt": "2026-07-01T08:17:51Z"
  },
  "sourcePromptId": "reading-neutral-hidden-signal-summary",
  "promptCode": "manual-client-perplexity-20260625-001-p22",
  "confirmedHitFromPrompt": false,
  "rawEventIds": [
    "mr1sz0ij-40c07r8l"
  ],
  "events": [
    {
      "id": "mr1sz0ij-40c07r8l",
      "timestamp": "2026-07-01T08:17:42.306Z",
      "path": "/robots.txt",
      "userAgent": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot)"
    }
  ],
  "resourceCounts": {
    "targetPageRequests": 0,
    "robotsRequests": 1,
    "rootRequests": 0,
    "trackingPixelFetches": 0,
    "nonPixelSubresources": 0,
    "clientCapabilityEvents": 0
  }
}
```

## Interpretation

This run does not show Perplexity reading the p22 target page. The response
reported a fetch failure, and the bounded origin review found no exact
attempt-id or fixture-path request during the prompt window.

The run also is not a pure no-hit result. PerplexityBot requested
`/robots.txt` shortly before the answer appeared. Because that request lacked
the attempt id and did not open the target path, it is evidence of
prompt-window site contact, not evidence that the target page or its visible,
meta-description, or JSON-LD signals were inspected.

## Limitations

- This finding covers one Perplexity run, one account/session, one native
  incognito thread, and one fixture.
- The prompt supplied the exact target URL, so the run tests direct opening,
  not independent discovery.
- The Perplexity UI exposed a generic `Model` selector but not a precise model
  name in the captured snapshot.
- The recorded start and end times are operator-side bounds around submission
  and final answer observation, not service-internal fetch timestamps.
- Origin review used the local `/api/hits` view during the bounded window; it
  would not capture a delayed target fetch outside that window.

## Publication Thesis Verification

- Thesis: Perplexity native incognito did not fetch the p22 neutral
  hidden-signal target page during this controlled-browser attempt, although
  PerplexityBot did request `/robots.txt` inside the same prompt window.
- Source: Fresh Perplexity incognito response, generated response and answer
  artifacts, browser-task artifact, preflight output, and bounded `/api/hits`
  review.
- Method: Exact public target preflight, controlled-browser use of a fresh
  Perplexity incognito thread, prompt submission, exact attempt-id review,
  fixture-path review, `/robots.txt` review, root-path review, and bounded
  timestamp-window correlation.
- Bias: Single run, Free plan, generic model selector, and Perplexity's
  retrieval implementation may vary by account, region, product surface, or
  time.
- Consensus: Consistent with Finding 044, where Perplexity missed the p20
  target page while touching `/robots.txt` and `/`, and with Finding 048,
  where Perplexity did not fetch the p21 hidden structured-data target page.
  Contrasts with Finding 053, where Claude fetched the same p22 target and
  exposed visible plus meta-description text.
- Invalidation: A raw event for the exact attempt id or fixture path inside
  the same prompt window, a response artifact from the same attempt showing
  retrieved page content, or a fixture/preflight mismatch would weaken this
  result.
- Verdict: Supported for this run. The copied Perplexity answer, empty
  target-path review, and prompt-window PerplexityBot `/robots.txt` event
  align with a target-page no-hit plus ancillary origin contact.
- Additional tests suggested: run the remaining Copilot/Bing p22 task to
  complete the client set, then compare p22 no-hit and ancillary-origin
  patterns with p20 and p21.

## Next steps

- Run the Copilot/Bing p22 controlled-browser task in a fresh native temporary
  chat.
- Compare Perplexity p20, p21, and p22 as a scoped no-retrieval pattern for
  this account, mode, and fixture family.