SHARE-TEXT PUBLIC ARCHIVE — BOUNDED LISTING ENUMERATION 2026-09-05 UTC. No verified second actor. 60 listing pages retrieved; halted on page61 HTTPError. WHAT WAS ACTUALLY COVERED https://share-text.org/zh/public-notes and discovered next links ?page=2 through ?page=60, all saved. Each page had 12 entries; 720 entries and 720 distinct displayed IDs. Claimed dates run July20 through September5, 2026. September:102 entries; August:467; July:151. Of these, 690 display dates before September4 and 30 display September4–5. May, June and July1–19 remain uncovered. This corrects the bot's estimate of a 53-page archive: page53 had an actual next-page link and the sequence continued to page60. Page60 also had a next link. Therefore this was not the archive's end and must not be described as full enumeration. The crawler made sequential GETs only and waited at least 1.6 seconds before each request after page1. It followed actual pagination links, never guessed note IDs. The authorized ceiling was 80 pages; it stopped earlier on an HTTPError at page61 and made no retry or subsequent origin requests. A logging defect retained only the exception class, not the HTTP status or error body, so we cannot distinguish a rate limit, challenge, missing page or other HTTP failure. Treat older coverage and full-note verification as interrupted, not negative. Raw listings: pastebins/data/share-text.org/china-codex-list-001.html through -060.html. Per-fetch JSONL metadata with URL, UTC, HTTP status, bytes, SHA256 and file path: pastebins/data/share-text.org/china-codex-fetch.jsonl PRIVATE listing extraction (URLs, IDs, claimed dates, snippets and displayed lengths): pastebins/data/share-text.org/china-codex-entries-internal.jsonl Do not publish that file or the raw listings without redaction: other entries contain callback codes, VPN configurations and credential-like material. Such note bodies and embedded callback URLs were not visited. Safe coverage/date-count summary: investigation/china/009-share-text-summary.json Reproducible crawler: investigation/china/crawl-share-text.py DATE STRENGTH All 720 IDs parse as Unix-millisecond numbers whose UTC calendar date agrees with the displayed date. This is internal consistency, not independent proof of creation time: both fields are controlled by the same service. Capture time on our fetches is independently recorded locally but occurs September5. None of the candidates below has an independently obtained pre-disclosure archive snapshot. Pagination produced zero duplicate IDs. Offset pagination can still omit/move entries if new posts arrive during a crawl; distinct counts alone do not guarantee a perfectly frozen census. REVIEWED PRE-DISCLOSURE LISTING CANDIDATES These are explicitly SNIPPET-ONLY candidates, not verified full-note findings. Full-note reads were deferred when the host returned an error. Classification below concerns what the listing actually shows. A. July24 — orchestration/QA prompt, highest follow-up value in this sample https://share-text.org/zh/view/1784928797078 Listing page56, claimed 8611 characters. Reviewed marker: QA_REPORTING. The visible introduction describes receiving input from a named QA tester during active testing in a multi-agent pipeline. Why it deserves a look: explicit multi-agent workflow text and a claimed pre-disclosure date. Why it is not swarm evidence: this can be an ordinary developer sharing an orchestration prompt. The snippet has no anonymous source-fetch experiment, scratch-memory instruction, external data endpoint, or cross-host marker join. No basis to identify a Chinese lab or prove autonomous publication. Full body not inspected. B. August15 — planner/subagent configuration https://share-text.org/zh/view/1786814922347 Listing page29, claimed 14638 characters. Snippet starts PLANNER and describes an architecture/planning specialist, with mode: subagent and model: openai/gpt-5.6-sol. Likely ordinary agent configuration pasted by a developer. An OpenAI model setting does not establish who posted it, an OpenAI lab actor, or a Chinese actor. Full body not inspected; no verified behavioral link. C. August12 — local code-review agent project specification https://share-text.org/zh/view/1786512846388 Listing page35, claimed 3150 characters. Title is AI-Powered Local Code Review Agent and introduction is a problem statement about developing complex Python scripts locally. This reads as a project specification rather than a research agent's externally stored scratch state. Full body not inspected. D. August17 — codebase-refactor planning prompt https://share-text.org/zh/view/1786989005653 Listing page28, claimed 10941 characters. Visible content asks to simplify/refactor an existing codebase while preserving behavior. This is ordinary human-to-assistant coding instruction at snippet level. Full body not inspected. E. September2 — Chinese AI answer about inability to generate download links https://share-text.org/zh/view/1788323055507 Listing page7, claimed 4825 characters. Visible answer says it cannot create a cloud-document download link and offers copying Markdown examination papers into Word/WPS. This is Chinese-language AI output with an external-link limitation, but its visible workaround is normal user copying. It does not show the agent creating this paste or experimenting with remotely writable surfaces. Full body not inspected. Other visible false-positive classes include one-word test/test123 pastes, SQL view names containing TEST, payment-support/debugging references, a commercial support chatbot transcript, software-agent installation commands, marketing copy and ordinary Chinese examination material. These are not independent research-agent observations. Credential/VPN/callback entries were excluded from candidate-body consideration, and their contents are not reproduced here. CONCLUSION AND NEXT STEP This surface provides a usable multilingual public archive and is worth a later resume after the access failure is understood. Priority reads are A, then B/C if the host is available again; stop if the response is authentication or a challenge. Obtain independent dated captures and look for actual research behavior before attributing any candidate. Resume discovered page61 only after an appropriate pause/access assessment; no reason to enumerate guessed numeric IDs. The Chinese UI is a localization choice, not evidence of Chinese ownership, user nationality or a Chinese lab. No candidate in this bounded pass meets the standard for a second actor, and no swarm-positive addition was made to NEW_SITES.md. FOLLOW-UP AUGUST LISTING ANCHOR (report016) The later exact-marker surface scan discovered an archived default-locale public listing, https://share-text.org/public-notes?page=19, captured2026-08-10 07:53:02 UTC. It explicitly links candidateA /view/1784928797078 with QA_REPORTING, July24 displayed date and8611characters. This independently anchors the listing before disclosure, superseding the earlier statement that no candidateA pre-disclosure snapshot had been obtained. A historical full-note body remains unavailable. Coordinator subsequently recovered the current full body (report019): reusable QA prompt, blank output fields, no URLs; current content is not proof of unchanged August body. CandidateB remains without such an archive anchor. See016-surface-pivot-scan.txt and safe-candidate-A-anchor.json under pastebins/data/share-text.org/surface-pivot-archive/.