# Finding 098: Copilot/Bing clean no-hits stayed stable across four head-signal runs ## Date 2026-07-03 ## Status Published ## Summary This comparison reviewed four completed Copilot/Bing plain head-signal runs: `manual-client-copilot-bing-plain-head-signal-20260702-001-p37`, `manual-client-copilot-bing-plain-head-signal-repeat-20260702-001-p38`, `manual-client-copilot-bing-plain-head-signal-randomized-repeat-20260703-001-p43`, and `manual-client-copilot-bing-plain-head-signal-randomized-repeat-20260703-001-p44`. All four prompts asked Copilot/Bing to open the supplied `/lab/reading/head-signal-isolation` URL and give a brief site-owner review, without asking for source areas, page-head metadata, structured data, code-like tokens, marker values, or hidden fields. All four copied answers returned `fetched:false`, `pages_opened:0`, and evidence quote `Failed to get web content.` The direct-origin evidence also stayed stable: none of the four bounded prompt windows contained an exact target-page hit for the requested URL, and none contained related Copilot/Bing root, robots, sitemap, or exact target-path activity. p44 was the strictest no-contact window because the bounded prompt window contained no origin events at all. | Attempt | Answer-side result | Direct-origin target hit | Ancillary origin activity | |---|---|---|---| | p37 | `fetched:false`; `Failed to get web content.` | None | None | | p38 | `fetched:false`; `Failed to get web content.` | None | None | | p43 | `fetched:false`; `Failed to get web content.` | None | None | | p44 | `fetched:false`; `Failed to get web content.` | None | None | ## What does this mean? For site owners, SEO/AEO teams, publishers, and researchers, Copilot/Bing repeatedly said it could not retrieve the supplied page and the lab repeatedly saw no matching origin contact during the measured windows. That makes this different from a client that fetches a page but gives a weak answer: for these four runs, the server-side evidence supports a clean no-hit pattern. The result is still scoped to one fixture, account mode, and prompt family, so it should be used as repeated evidence for this condition rather than as a universal Copilot/Bing access rule. ## Method This comparison uses the published p37, p38, p43, and p44 findings and their response artifacts: - Finding 082: Copilot/Bing p37 plain head-signal clean target no-hit. - Finding 085: Copilot/Bing p38 repeat clean target no-hit. - Finding 095: Copilot/Bing p43 randomized repeat clean target no-hit. - Finding 096: Copilot/Bing p44 randomized repeat clean target no-hit. Each run was submitted in a fresh Copilot Temporary chat from the logged-in OpenClaw-controlled Chrome profile, copied into the matching response artifact, logged with `npm run manual-client:log`, and reviewed against local direct-origin events inside a bounded timestamp window. The p43/p44 randomized pair repeated the same short id-only target URL shape as p37/p38 after the first repeat set was complete. ## Evidence | Evidence type | Result | |---|---| | Copied answer stability | p37, p38, p43, and p44 all reported failed page retrieval with `Failed to get web content.` | | Target-page retrieval | No exact `/lab/reading/head-signal-isolation` target-page hit appeared in any of the four bounded prompt windows. | | Ancillary activity | No related Copilot/Bing `/`, `/robots.txt`, sitemap, or exact target-path activity appeared in any of the four bounded prompt windows. | | Client context | All runs used a visible Copilot Temporary chat on the `kai` account, Free plan, and `Smart` response mode. | ```json { "comparedAttempts": [ { "promptCode": "manual-client-copilot-bing-plain-head-signal-20260702-001-p37", "confirmedHitFromPrompt": false, "rawEventIds": [], "ancillaryOriginActivity": { "present": false, "paths": [], "rawEventIds": [] } }, { "promptCode": "manual-client-copilot-bing-plain-head-signal-repeat-20260702-001-p38", "confirmedHitFromPrompt": false, "rawEventIds": [], "ancillaryOriginActivity": { "present": false, "paths": [], "rawEventIds": [] } }, { "promptCode": "manual-client-copilot-bing-plain-head-signal-randomized-repeat-20260703-001-p43", "confirmedHitFromPrompt": false, "rawEventIds": [], "ancillaryOriginActivity": { "present": false, "paths": [], "rawEventIds": [] } }, { "promptCode": "manual-client-copilot-bing-plain-head-signal-randomized-repeat-20260703-001-p44", "confirmedHitFromPrompt": false, "rawEventIds": [], "ancillaryOriginActivity": { "present": false, "paths": [], "rawEventIds": [] } } ] } ``` ## Interpretation The four-run Copilot/Bing set supports answer-side stability, target-page no-hit stability, and clean origin-side no-hit stability. Copilot/Bing repeatedly said it could not fetch the supplied page, and the lab repeatedly saw no exact target-page hit or nearby Copilot/Bing origin contact inside the bounded prompt windows. This differs from the sibling Perplexity p37/p38/p43/p44 sequence in Finding 097. Perplexity also repeated failed-fetch answers and exact target no-hits, but its ancillary origin footprint alternated between root/robots contact and clean no-hit windows. Copilot/Bing stayed clean across all four reviewed windows. Because none of the four runs fetched the exact target page, this comparison does not make claims about visible body text, page-head metadata, hidden markers, robots compliance beyond observed non-contact, or structured-data visibility. It only compares failed-fetch answers, exact target no-hits, and nearby first-party origin activity. ## Limitations - This comparison covers four Copilot/Bing runs from one account, Free plan, web surface, fixture, response mode, and prompt family across two days. - The prompts supplied exact target URLs, so this measures direct URL opening rather than independent discovery. - The clean no-hit windows are bounded to retained local event logs; they cannot prove that no unobserved backend attempted retrieval elsewhere. - The evidence does not explain whether the failed fetches came from product routing, retrieval backend state, robots handling, connection timing, or another condition. - The high-level OpenClaw browser `act` wrapper had a known targetId mismatch on several Copilot tabs, but the prompts were submitted through the same fresh visible tabs by direct browser control. ## Publication Thesis Verification - Thesis: Across p37, p38, p43, and p44, Copilot/Bing repeated failed-fetch answers, exact target-page no-hits, and clean origin no-hit windows with no related root, robots, sitemap, or exact target-path activity. - Source: Findings 082, 085, 095, and 096; their browser-task artifacts, response artifacts, logged answer packets, and bounded direct-origin event reviews. - Method: Compare copied answer fields, prompt codes, source prompt ids, bounded timestamp windows, confirmed target raw event ids, and `ancillaryOriginActivity` fields across the four completed Copilot/Bing runs. - Bias: Small synthetic-fixture set from one logged-in account, plan, and response mode. The prompts are plain relative to source-area prompts but still provide exact lab URLs and ask for an AI-assistant readability or site-owner review. - Consensus: Internally consistent with each individual finding. All four copied answers report failed fetches; all four origin reviews have `confirmedHitFromPrompt:false`; none list related ancillary origin event ids. - Invalidation: A corrected origin review finding an exact target-page event or related Copilot/Bing ancillary event in any prompt window, a response artifact assigned to the wrong prompt, or evidence that the timestamp windows missed product-origin activity would weaken the comparison. - Verdict: Supported for the completed Copilot/Bing p37/p38/p43/p44 plain head-signal set. The strongest claim is repeated clean no-hit behavior in this measured condition, not broad Copilot/Bing access behavior. - Additional tests suggested: prepare a later mixed-client no-hit packet only if the lab needs to test whether Copilot/Bing's clean no-hit pattern changes under a new fixture, account state, or response mode. ## Next steps - Keep future Copilot/Bing follow-ups focused on conditions that could change retrieval routing, such as indexed versus unindexed pages, account mode, response mode, or delayed discovery windows.