Scribd citation-marker pivot: reproducible snippets, no verified cross-source join Reviewed 2026-09-05 UTC ASSESSMENT DOC1-SEC1-P0 and DOC2-SEC1-P0 remain an unresolved snippet-only lead. Fresh Google/Serper results reproduce the same two Scribd documents; no exact non-Scribd or GitHub match was returned in this bounded pass. No uploader, reliable upload date, model/operator identity, or actual citation-testing workflow was recovered. The numbered document/section/paragraph-like naming and generic explanatory prose are consistent with synthetic document/RAG testing or a human-authored fixture. That is a plausible alternative, not a verified classification. No known-thread-A join was found in the specifically checked local wiki export, but a non-match does not establish a new actor or Chinese origin. ORIGINAL SOURCE PROVENANCE https://www.scribd.com/document/1041205392/scribd-upload-document-1 https://www.scribd.com/document/1041205258/scribd-upload-document-2 Original CN26H010 tool observations show search-result titles identifying upload documents1 and2, categorised by the index under Reliability Engineering. Document1's snippet combines its marker with generic resource-allocation prose. Document2's combines its marker with generic incremental-improvement/sustainability prose. The displayed results contain no uploader or publication-date field. “Reliability Engineering” is an indexed title/category, not independently inspected document content. The already-retained direct fetches are HTTP200 Client Challenge pages, observed11:34:31Z and11:35:41Z on September5. Their identical retained-body hash was documented in031. Those fetches do not verify the snippet text inside the actual documents. The prior archive lookup failed. This task made NO Scribd requests and did not attempt an alternate access route or challenge bypass. NEW SEARCHES — EXACTLY EIGHT Alternate web-search interface: 1. "DOC1-SEC1-P0" 2. "DOC2-SEC1-P0" 3. "DOC1-SEC1-P0" OR "DOC2-SEC1-P0" -site:scribd.com 4. site:github.com "DOC1-SEC1-P0" OR "DOC2-SEC1-P0" This interface returned unrelated broad matches involving protein names DOC2/SEC1 and other partial tokens, not verified literal markers. These are search fallback/noise observations. They must not be treated as exact cross-source matches or a precise exhaustive zero count. Google/Serper, default locale, num10: 5. "DOC1-SEC1-P0" OR "DOC2-SEC1-P0" At11:42:12UTC, organic array contained exactly the two existing Scribd URLs with the same markers and generic prose. Neither returned a date field or uploader. 6. "DOC1-SEC1-P0" OR "DOC2-SEC1-P0" -site:scribd.com At11:42:14UTC, explicit organic array present and empty. 7. site:github.com "DOC1-SEC1-P0" OR "DOC2-SEC1-P0" At11:42:17UTC, explicit organic array present and empty. 8. "Unique reference marker" "DOC" -site:scribd.com At11:42:19UTC, two broader hits: Apache Traffic Server documentation and a Springer proceedings PDF. Neither returned an exact DOC1/DOC2 marker match in its result. The proceedings PDF was not fetched. The empty arrays are successful recorded search responses, not access errors; they still do not prove absence from an incomplete/ranked index. GitHub was searched through the public search index, not authenticated or exhaustive GitHub code search. ONE OTHER-HOST VERIFICATION GET https://docs.trafficserver.apache.org/en/latest/developer-guide/documentation/conventions.en.html The official Apache page explains documentation conventions, including section reference labels in reStructuredText. This resolves the generic wording hit as ordinary documentation terminology, not the Scribd markers or an agent test. No other source GET was needed. Total for this task:8 queries,1 other-host verification GET,0 Scribd GETs,0 Ubuntu GETs. Search API requests were retrieval operations; no target publishing or source-code execution occurred. LOCAL KNOWN-CLUSTER CHECK Exact literal marker comparison against four already-downloaded collusion wiki exports scanned42,186 JSON records:14,591 revisions,4,579 pages,3,103 labels and19,913 events. Neither marker occurred. This is a bounded absence-of-literal-join observation on a selected known-wiki corpus; it does not cover every known thread-A artifact, deleted page, package, paste or paraphrased marker. DISCRIMINATORS STILL MISSING - A readable original document or independent dated capture establishing full content and uploader context. - The exact marker appearing in a public test repository, issue, manifest or another independent surface with provenance. - A documented posting/retrieval sequence linking these documents to an actual agent research task. - Evidence identifying an operator/model separately from document language and naming. Without these, neither “known A” nor “Chinese second actor” nor “confirmed human RAG fixture” is justified. Do not spend more identical requests on the already-challenged Scribd routes. A genuinely new indexed cross-source occurrence would supply a better pivot. ARTIFACTS Original observations: swarmhunt/runs/CN26H010.log and cached challenge responses. Prior reviewed distinction: investigation/china/031-global-behavior-review.txt. Fresh Serper query/result metadata: investigation/china/035-search-records/query-5.json through query-8.json (no credentials). Local literal-join counts: investigation/china/035-search-records/local-join.json. The current top website lead card remains based on reviewed Ubuntu report028; these snippets were not promoted to a confirmed actor or stronger lead assessment.