092 — Completed archive copy scan: no literal-prefix candidates
Reviewed September 5, 2026, 20:54 UTC. Supersedes the running status in report 091.

Result
The existing August Common Crawl text corpus scan completed in 659 seconds: all 100,000 manifest files, 2,083,525,558 text records, zero failed files and zero matching records. No input bytes were downloaded. The process exited; its bounded status observer also finished. There is no continuing copy-scan job.

What was searched
The 5,802 case-sensitive patterns represent leading 62–64-character substrings of the original and space-to-plus forms of 3,571 opaque xinzhai/xz records. These patterns can identify literal copies under different labels. The prefix material remained private and was not submitted to public search engines. Report 091 documents normalization, source provenance, the isolated scanner and preflight checks.

Completion audit
The final done.txt has exactly 100,000 distinct paths and equals the input manifest as a set: zero missing or unexpected paths. failed.txt, scores.tsv and matches.tsv are each zero bytes; domains.tsv contains only its header. The terminal log independently reports the same complete file count, page count and zero matches. Private final-audit.json records file sizes and SHA-256 hashes, audited at 2026-09-05T20:53:56.737272+00:00.
Manifest SHA-256: 14e2fec6029971c0f1807162ae482fd69c3929a33bef9aa4ff0f49c4c6cea35d
Completed-path file SHA-256: a22184199ca068c273b3b4d9c50465d239593cd25d9f03f1a403ada29059e121
Pattern file SHA-256: 1e8e95f607c4411e31beaf399c23ac00c2bc66ba63a37b81f8a16f1bc36b7775
Terminal log SHA-256: 0fe1acecb73e0d4272ee942272854e0cd02baa0d467f552de8f41f693037ed8a

Interpretation
This found no cross-host copy candidate in this corpus under the tested literal forms. It neither weakens the strong within-host xinzhai/xz workflow link nor establishes that no copies exist elsewhere. Common Crawl text extraction omits content; line wrapping, entity changes, inner encodings and newly encrypted copies can defeat these patterns. The source host's archived crawler exclusion further limits coverage. No full-record match or independent attribution was discovered.

The best current interpretation remains a related publishing workflow: bulk version-labelled opaque uploads interleaved with smaller knowledge-labelled records, followed by periodic records and plan-associated size changes. This is compatible with automated storage, but does not establish a swarm, Chinese laboratory, model identity, or the meaning of its contents.

Private provenance: investigation/china/091-private/final-audit.json and the same remote output directory /data/runs/china-codex-xz-copies. The existing archive corpus was preserved. No original-site requests, posting, decryption or key search occurred in this scan.