LOCAL CORPUS AUDIT — CHINESE / SECOND-ACTOR HUNT
Updated 2026-09-05 UTC. Read-only audit; no target requests or modifications.
Status: completed. No verified second-actor candidate found by this audit.

1. Measured scope, not an internet-wide negative
pastebins/analysis/pastes.jsonl contains 47,079 metadata records across 20 hosts. 42,615 (90.5%) are geopaste.scratchbook.ch; the remainder are 4,464 records. Only 2,682 (5.7%) records have a nonempty extracted date, which is not itself proof of publication time. Only 23 titles contain CJK characters. These numbers make the local sample poorly suited to ruling out a Chinese ecosystem.
The metadata index omits body text. This audit therefore resolves each record to its original raw file before applying Chinese-language and Chinese-endpoint detectors. html.cafe and wiki exports are separate corpora, not included in the 47,079 count.

2. Saved Common Crawl scans independently recounted
Source directory: pastebins/agents/coord/china/.
china30-scores.tsv: 1,886 rows, 411 domains.
china34-scores.tsv: 18,329 rows, 3,021 domains.
The 66 exact terms in terms_china.tsv mix test phrases, statistical endpoints, and proxy chains. Those categories should not be summed as evidence of agent behavior. Reproducible per-term counts are saved in 003-china-scan-summary.json.
July: phrase matches include Agent测试 202, 智能体测试 31, LLM测试 21, 链接格式测试 1. A single commercial product domain, xiaoduoai.com, accounts for 185 phrase-bearing rows.
August: Agent测试 5,365, 智能体测试 507, LLM测试 868, 临时测试页面 6, 自动化测试页面 3, 智能体 引用 2, 参考链接测试 1. xiaoduoai.com alone accounts for 5,036 phrase-bearing rows; aliyun.com contributes 785. Rows from a repeated template are not independent actor observations.
No listed proxy-wrapped Chinese government/statistics endpoint has a hit in either saved crawl. Standalone cors.zme.ink and cors.eu.org each have one August hit; neither is a proxy-plus-Chinese-endpoint match.

3. Small residual CC leads, explicitly unverified
These deserve page-context review rather than a second broad exact-marker sweep. Only URLs and matching terms exist locally in these score files; dates below refer to the crawl family, not page creation.
https://www.cilimiao.cn/ — July — 链接格式测试. A homepage-level one-off; likely ordinary tool test, unverified.
https://htmldrag.com/zh/guides — August — 临时测试页面. Hosting/tool documentation, potentially useful for finding a publishing surface but not an agent artifact.
https://www.ssoocc.com/64182.html — August — 参考链接测试. Context unverified; single rare phrase.
https://www.1itao.com/image-anti-leech.html — August — cors.zme.ink. URL indicates anti-hotlinking tutorial; proxy infrastructure lead only.
https://www.netnr.eu.org/279 — August — cors.eu.org/. Proxy infrastructure lead only.
Other rare-phrase URLs are clearly documentation/article shaped: zhangbh.com/posts/build-astro-blog/, AWS Device Farm documentation, wiki.apipost.cn/docs/changelog/, apifox.com/blog/features-2022-8/, ittrends.news/.../robots.txt.html. No anonymous artifact has been established.

4. Corrections to inherited labels
swarmhunt/runs/C03.md calls the Chinese wiki sweep NEGATIVE, but Huiji and MoeGirl were completely inaccessible. Those are BLOCKED / UNKNOWN coverage. Qiuwen was CAPTCHA blocked; FurryWiki returned 468. The score does not become a negative merely because Google exact-marker queries returned zero.
Conversely, C03 documents successful BWiki API access (200 JSON), despite the handoff broadly grouping BWiki among blocked sources. It read 50 dsp recent changes in May–August 2026, 30 portal rows, one other game's recent changes, and searched a few game wikis. This is useful limited coverage, not a census of the farm. Read-only per-game API enumeration can be attempted before buying infrastructure.
N17's alleged second-actor IP 2.210.160.68 edited AgentTexasPovertyNacLufHendJackX1 on September 4 with summaries [revert to revision 1.0] and [GET-only edit mechanism test]. This belongs in probable post-disclosure contamination, not pre-disclosure lab evidence. Source: swarmhunt/runs/N17.md and findings.jsonl entry timestamp 2026-09-05T09:24:38Z. URL: https://www.wikiservice.at/probier/wiki.cgi?action=browse&diff=4&id=AgentTexasPovertyNacLufHendJackX1
HK bp/global47 shortener activity remains excluded as known spam/tool probing. Chinese words, ISP geography, and cloud ownership alone cannot establish a Chinese lab or even a research agent.

5. Better next discriminators
Search for behavior across languages: repeated harmless link-format tests, URL-encoding variants, failed fetch workarounds, task-specific source citations, scratch-memory instructions, and rapid cross-host joins. Require an independently anchored pre-disclosure date plus at least one behavioral join before attributing an actor cluster. Distinguish a new surface used by the known actor from a second actor.
Do not demand Chinese language or mainland endpoints: an overseas Chinese-model evaluation may use English and international datasets. Conversely, Chinese comments plus Jina tutorials are ordinary developer content.
Improve date recovery from raw page metadata and archived captures before interpreting the 94.3% undated metadata sample. Prioritize coverage of actual public listings and revision histories over more guessed Agent*/zz* slugs.

6. Completed raw-body screening
All 47,079 metadata records resolved to a readable original file; zero missing. 76 files contain at least five CJK characters, a weak language signal because CJK can also be Japanese text. The test/temporary/agent/shared-memory Chinese-language and pinyin screen selected 209 files. No raw file matched the selected Chinese statistics/disclosure/court/HK endpoints or cors.zme/proxy.sunly strings. Independently, extracted URLs in all 47,079 metadata records had zero such endpoint matches.
False-positive discovery: bare ceshi matches English spaceships, apprenticeships, NiceShipping; linshi matches amoxicillinshipped in pharmacy spam. These must use Latin-letter boundaries, not naked substrings. With boundaries, only three test-language candidates remain:
(a) https://geopaste.scratchbook.ch/view/1181c846, title 测试123, body testtesttest测试. Saved view HTML says “From Gruff Bongo, 8 Years ago”; this is an old ordinary test, not a 2026 agent artifact. Date is relative in the captured page, not independently anchored. SHA256 of raw file: bf9a528f32895fd22c0aa55e331d88c93b7d8d5b500c2636e971c473e3e6348f. The raw file is ~62 KB largely because it includes PHP deprecation messages before the tiny paste body; raw file size must not be treated as authored content size.
(b) https://paste.steamr.com/view/06fcb018, title POST bots: an HTTP path-count list includes /ceshi.php among common PHP scanner targets. This is bot/scanner-log vocabulary, not research-agent scratch memory. No extracted publication date.
Files: 003-local-screen.jsonl records broad-screen hits, and 003-screen-refined.json records the three boundary-corrected hits. These are detector outputs, not positive actor candidates. 003-endpoint-metadata.json is an empty array (zero matches). Keep raw excerpts internal until any publication redaction pass.

(c) https://geopaste.scratchbook.ch/view/b9b07345, Untitled: repeated POST /tomcat.php, /ceshi.php, /1hou.php, /ou2.php return 404 in server logs. Same generic PHP-scanner false positive; no research-agent pattern or publication date.

7. Subsequent limited live-context checks (read-only, 2026-09-05)
After the local audit, during the follow-up scan task, web open retrieved https://www.cilimiao.cn/ as a large BT/website-directory homepage; the exact old match 链接格式测试 was absent in current extracted text. https://htmldrag.com/zh/guides returned a product usage guide; 临时测试页面 was absent in current extracted text. These do not establish anonymous artifacts. https://www.ssoocc.com/64182.html failed to fetch and remains unverified. No target forms or write-like links were followed.