REVIEWED — SURFACE LINKS SCAN COMPLETE
Reviewed 2026-09-05 UTC. No new rare-candidate source or verified second actor found.

COMPLETE COVERAGE
One August text-plus-links pass finished in1,604seconds (26min44sec).
100,000/100,000 WET-manifest files processed;0 failures.
2,083,525,558 text pages examined with corresponding existing links extracts.
3,940 matching page rows across102 registrable source domains.
0 bytes downloaded; all100,000 text files and100,000 links files were present at preflight. No malformed final result rows.
Remote PID171673 exited after completion. No repeat job, new corpus, target write or infrastructure change. EC2 remains running.

PRIMARY CANDIDATE RESULTS
1785436446544 (unreadable bridge destination):1 text hit,0 link hits. The sole text source is the already archived https://textshare.online/d4622e/. Its destination URL is plain text, not an observed clickable href in the links extract. No new source or body recovery resulted. Report020's destination HTTP503/no-capture limitation remains UNKNOWN, not a negative actor finding.
1784928797078 (candidateA QA_REPORTING):0 text hits,2 link hits. They are the already known https://share-text.org/public-notes?page=19 and https://share-text.org/ru/public-notes?page=19, linking respectively to /view/1784928797078 and /ru/view/1784928797078. Relative hrefs were resolved against the source URL and actual host/path validated. These are two localized listings on the same surface, not two independent actor events. Report016's August10 archived listing anchor and report019's current reusable QA-template review remain the appropriate disposition.
1786814922347 (candidateB planner configuration):0 text or link hits. No new date or body evidence.
textshare.online/d4622e/ (exact source-page reference):0 text or link hits from other page content/links. Its own page's presence does not imply someone linked to it: ccsearch terms are matched against body/links, not the source URL field.

Thus only2 validated candidate-target href examples from2 source pages exist in final results; both are previously reviewed same-surface listings. There are0 new external candidate-target href sources. The separate known cross-surface plain-text reference is real but its purpose and destination content remain unknown.

REVIEW SCOPE
Manually inspected all3 rare-term matching rows and their JSON link evidence. Reused already recovered archived bodies/metadata from016 and020; no redundant target/archive fetch was necessary. This review used0 of the permitted6 new retrievals. No generic directory/spam bodies were re-triaged. Broad service references and own-site navigation do not establish research-agent behavior.

HOST-BOUNDARY VALIDATION
Link-term counts include href strings and anchor text. The parser resolves relative hrefs, then validates parsed target hostname exactly; merely embedding the desired URL in another host's query or anchor is not a direct target link. This removed76 non-target-host netcut evidence examples and66 note.ms examples from direct-link counts. Examples are capped by ccsearch at3 per term per source page, so validated example/source-page totals are lower bounds where output evidence is capped. They are not a complete inventory of all hrefs in each original page.
Case-sensitive exact terms, Common Crawl sampling, expired/unindexed/private pages and missing full target content still limit recall. The result cannot establish that no Chinese, English-speaking Chinese-model or other research swarm exists.

FINAL COUNTS
Columns: term | text-page hits | link-page hits | distinct source pages with a validated direct target href (from saved evidence).
1785436446544 | 1 | 0 | 0
1784928797078 | 0 | 2 | 2
1786814922347 | 0 | 0 | 0
textshare.online/d4622e/ | 0 | 0 | 0
//share-text.org/ | 8 | 630 | 629
//textshare.online/ | 2 | 267 | 267
//textdb.online/ | 0 | 0 | 0
//api.textdb.online/ | 0 | 0 | 0
//webnote.cc/ | 7 | 11 | 11
//netcut.cn/ | 95 | 1866 | 1790
//getnote.top/ | 3 | 7 | 7
//paste.ubuntu.org.cn/ | 9 | 6 | 6
//note.ms/ | 79 | 163 | 96
//www.netnr.eu.org/ | 1 | 1048 | 1048

REPRODUCIBILITY
Terms: investigation/china/terms_china_codex_surface_links.tsv (14 terms).
Remote output: /data/runs/china-codex-surface-links.
Local raw scores/log/domain aggregation/generated report: investigation/china/cc-surface-links/.
Safe term counts:023-link-summary.json. Rare source/href pairs:023-candidate-links-internal.json.
Parser: summarize_surface_links.py. Bounded completed monitor: monitor_surface_links.py. Original launch method/progress details preserved in023-initial-methods.json.
Command: ./target/release/ccsearch --corpus /data/corpus --links /data/links --s3 --s3-endpoint http://s3.us-east-1.amazonaws.com --crawl CC-MAIN-2026-34 --concurrency 384 --out /data/runs/china-codex-surface-links --port 8097 --exit-when-done --score-terms /data/runs/terms_china_codex_surface_links.tsv --report-domains 100000 --report-pages 20000

Progress reports were automatically refreshed approximately every60seconds and labelled AUTOMATIC. This final assessment is analyst reviewed. Final DONE matches equal final score rows; earlier gaps came from per-file output buffering and non-atomic progress snapshots.