106 — Inner-encoding archive copy scan completed: zero candidates
Reviewed at 2026-09-05T21:39:31.169569+00:00. Supersedes running status104.

Verified result
All100,000input files completed in546seconds, covering2,083,525,558text records. Zero prefix candidates, zero failed files and no input downloads. The scan process and bounded observer have finished. This is the same corpus searched in092 with different representations; the two page counts must not be added as unique coverage.

Coverage and controls
The187patterns derive from the inner encoded text of9large xinzhai objects and76pieces, using URL-safe, standard Base64 and standard-plus-to-space representations. Two prefixes required edge trimming for the scorer; final lengths63–64characters. Report103 documents derivation and the separate local corpus check;104 records preflight and launch.
Report105 validated this exact pattern file and binary against189private synthetic records: all187planted patterns detected with their expected term IDs, both negative records excluded. Those planted matches are a scanner control, not web evidence.

Terminal audit
The100,000distinct done paths equal the input manifest exactly, with no missing or unexpected entries. scores.tsv, matches.tsv and failed.txt are each empty. The terminal log independently reports the same complete file count, record count and zero matches. The scanner is no longer alive.
Manifest SHA-256:14e2fec6029971c0f1807162ae482fd69c3929a33bef9aa4ff0f49c4c6cea35d
Done-path SHA-256:123bed613d4eef2e2a5ad172e5d9a8428b3e8f79f974348aa8c811ade2e43695
Pattern SHA-256:3fcaac4f963fe9181a86c3a6271097d3b3a1eb329aaded16899c8f1b900dd808
Terminal-log SHA-256:d96955418a17c13fb7c14a080fa470f85ca7dcba5f1412d986cbb98558146dd8

Interpretation
No inner-text copy candidate was found in the indexed text corpus under these tested forms. This closes the specific extra-Base64 representation gap left by092; it does not search all raw HTML/binary content, line-wrap or entity transformations, unindexed/deleted pages, or newly encrypted objects. It yields no plaintext or operator identity and does not weaken the independently observed within-host interleaving.
The strongest supported conclusion remains a related xinzhai/xz publishing workflow. Agent involvement, swarm size and Chinese-lab attribution remain unresolved.

Provenance and task state
104-private/final-audit.json preserves the terminal checks. The unchanged remote output is /data/runs/china-codex-xz-inner-copies; the control output remains separate. Existing archive corpus and092outputs were preserved. No original Ubuntu access, payload publication, key search or decryption occurred. No archive scan or OpenRouter wave remains running from this work;173terminal bot reports unchanged. The broader investigation remains active until user pause.