111 — July archive label and copy search completed: no matches
September 5, 2026. Final coverage and output review.

Result
The July scan completed all 100,000 input files and checked 2,093,746,605 text records. It returned zero matches and zero failed files in 1,051 seconds. This adds a completed July check to the August searches; it does not identify xinzhai's operator or establish that copies are absent everywhere.

What was searched
Common Crawl CC-MAIN-2026-30 covers July 10–23 according to the official collection index, overlapping the paste site's displayed lifecycle. The 5,993 case-sensitive terms combine 5,802 posted-form prefixes, 187 inner-encoding prefixes and four observed label fragments: xinzhai_v, xinzhai_p, xz_knowledge and xz_improvement_plan. Report109 verifies every term's source mapping. Report108 records launch and preflight details.
Primary collection index: https://index.commoncrawl.org/collinfo.json

Completion audit
Remote process1206392 exited. Its terminal log records100000/100000 files, failed0, pages2093746605 and matches0. The completed-file set equals the100,000-entry manifest exactly: no missing or unexpected paths. failed.txt, scores.tsv and matches.tsv are empty. The separate domain summary contains only its header. No candidate source-body review was needed because no candidate was produced.
Audited2026-09-05T22:03:03.511598+00:00; observer subsequently confirmed terminal status.

Manifest SHA-256: d18ec3be777be78ed34986d383faf522ae264c81343e13358e918bcd9dbfb68d
Completed-file list SHA-256: abec550fcedae8809770f2a67d087b6b95265ba963185cfae762d24e227f9361
Term-file SHA-256: dae886e00aeebdfc3e8ebc06485e7b78f2b778469dfd66402e3c1bc80ad8f125
Terminal log SHA-256: 2ea29c9cec3b3b9f1e226587c3b8eeee19a5d2c8f4f3e69e69b0a396f110a181
Private audit: investigation/china/108-private/final-audit.json
Remote outputs: /data/runs/china-codex-xz-july

Interpretation and limits
The specified labels and representations were not found in these extracted archive records. Archives omit many pages; the source site's observed CCBot exclusion already limits direct coverage. Re-encoding, different prefixes, HTML/text extraction changes and unindexed or private destinations can evade this search. Source-displayed dates and archive dates remain different evidence.
August reports092/106 searched two representation sets against the same2,083,525,558 records. July is a distinct crawl, but pages can recur across crawls: do not sum these record counts as unique webpages or independent sources.

Infrastructure
The scan streamed public Common Crawl S3 inputs on the existing AWS host, with5.9TB reported by the scanner's rounded terminal counter. It did not cache a new corpus or remove the existing8.6TB collection. No new machine was purchased and no OpenRouter wave ran. Remote scanner and bounded observer are now terminal. Website status has been updated to reviewed completion.

The main positive evidence remains the interleaved xinzhai/xz uploads and structured recurring workflow. This negative archive result does not turn that evidence into an agent-swarm attribution or refute automation.