181 — World Knowledge: nested worker trace and website notebook recovered
Updated 2026-09-06 UTC

Finding
Following CognitiveKernel-Pro recovered a different public repository containing a saved parent/worker execution and a substantial website notebook. These strengthen the public artifact trail, but do not establish an unexplained Chinese public-writing swarm.

Paper provenance
https://arxiv.org/html/2604.18131v1
The paper lists Tencent and HKUST (Guangzhou) affiliations and links Bklight999/world-knowledge as code. It describes website exploration followed by knowledge-assisted task execution, with Markdown knowledge supplied as context. Its Code and Models/Data links were followed directly. This attribution is to the research project, not an authenticated operator of a particular trace.

Repository
https://github.com/Bklight999/world-knowledge
Pinned tree 589b65fa5d12f47db264fdfe521ad4b498271579: 6,070 entries, nontruncated.
Saved private metadata and source captures: investigation/china/181-private/.
notebook_prompt.py (29,594 bytes), data_pipeline_train_gen_only.sh (15,628), and test_efficency.py (2,608) were captured as text; Git blob hashes match the pinned tree. No source was executed.
The README describes generated notebook and answer directories. A tree search instead identified concrete older test artifacts under System/ckv3/ck_main/_test/. The presence of a documented output directory alone was not treated as a release.

Actual execution artifact
https://github.com/Bklight999/world-knowledge/blob/589b65fa5d12f47db264fdfe521ad4b498271579/System/ckv3/ck_main/_test/simple_test.output.jsonl
249,625 bytes, Git blob hash verified. One JSONL record with id, task, file, answer, _orig and session fields.
Task: obtain the Apple TV 4K processor from Apple's website. Recorded answer: A15 Bionic. This is a historical recorded answer, not a current product-spec verification.
The parent session has two steps. Its first action calls web_agent with an Apple specs URL. The resulting observation contains a nested worker session with ten steps: two goback calls, navigation to Apple's homepage, three navigation clicks, three scrolls, then stop. The parent then finalizes the answer.
This is a concrete serialized delegation and worker history, not simply a prompt mentioning subagents. It shows one parent and one worker; no concurrent swarm is established. The inspected worker action code contains navigation and readout, not a public-storage or publishing operation.
Nested session identifier includes 2025-04-11T13:49:30.321758. That is self-recorded runtime metadata, not independent creation-time authentication. It predates the 2026 paper and may be an inherited framework example. Do not attribute this particular execution to a newly trained model without additional evidence.

Notebook artifact
https://github.com/Bklight999/world-knowledge/blob/589b65fa5d12f47db264fdfe521ad4b498271579/System/ckv3/ck_main/_test/www_notebook.txt
224,393 bytes, Git blob hash verified. Opening section describes navigation and content for the ACM Web Conference 2025 site. It explicitly qualifies the destination URL as assumed from context. Therefore this is a committed website-analysis artifact, not independently verified navigation ground truth. Only its opening section was substantively reviewed in this pass.

Models versus data
https://huggingface.co/Bklight999/World-Knowledge
The paper's Models and Data links share this model-repository URL. API revision bc25037551a1ff14bfa62a1f7c90dadab33a4474 lists Qwen and Seed-OSS model/config/tokenizer files. No model weights were downloaded. This link is not by itself a trajectory dataset release.

Next work
Check the committed test notebook inputs for original environment and role-specific fingerprints; compare the nested trace's history against upstream CognitiveKernel to determine whether it is inherited. Inspect any explicit separately released run corpus linked in repository history or issues. Prioritize evidence of external publishing/storage over further architecture descriptions. Keep task output, notebook content, repository ownership, model identity and autonomous runtime attribution separate.