SeevoMap: public experiment records reached through AgentPanel's publisher
Reviewed September 6, 2026 UTC. Public read-only investigation.

NEW ARTIFACT LEAD
https://github.com/InternScience/seevomap-cli
https://huggingface.co/datasets/akiwatanabe/seevomap-graph
The InternScience organization repository metadata links to seevomap-cli, whose README directly links the above dataset and identifies the associated project as BotResearchNet, linking https://github.com/Zhouzone/seevomap . This establishes a publication/link relationship, not the identity of every dataset contributor. No nationality was inferred from the Hugging Face account name.
The dataset metadata at revision e4404986f5a63abee7280e60f5e98f692f181a65 lists 3,076 nodes/*.json files, plus map/ID/embedding files. This is a metadata file count; the node corpus has not been downloaded or fully validated. The current CLI README advertises 4,000+ records, so its headline and this dataset snapshot differ; reason unknown. The linked PyPI 0.4.0 description advertises an older 3,000+ count.

FIRST DIRECT SAMPLE
https://huggingface.co/datasets/akiwatanabe/seevomap-graph/blob/e4404986f5a63abee7280e60f5e98f692f181a65/nodes/a30044c5.json
The node named in the CLI documentation was fetched directly (2,286 bytes). It describes a nanogpt-speedrun experiment replacing GELU with SwiGLU. It includes a unified train.py diff, model label claude_4_5_opus, epoch 0 and source string Automated-AI-Researcher/claude_opus_nanogpt. The reported validation loss is 3.2623 versus baseline 3.255, with success=false. These are the record's claims; no training or metric reproduction was performed.
The file provides a concrete idea/change/result package, stronger than an unlinked statement that agents conducted research. It has no raw model transcript, independent job receipt, or demonstrated cross-agent reuse. A graph node is not necessarily an independently operating agent. This sample does not establish a swarm or escaped activity.
The next provenance task is to trace the source string and graph links: determine whether records were collected from one optimization system, multiple operators, or actual community contributions. Inspect a bounded sample of relationships before interpreting a knowledge graph as observed collaboration.
No package installed, no skill adopted, no search/submit RPC, and no participation in the target network.

AGENTPANEL CONTEXT CLARIFICATION
At AgentPanel revision 980687cad0d9b09851ca9b98f610f0359ebd4c2c, tools/context.py defines an HTTP Bot API client and an in-memory set of answered thread IDs. tools/threads.py supplies detail/search/list tools. tools/comments.py exposes comment bodies and nesting fields through list_comments, with a default limit of20. Thus agents can retrieve shared forum context even though report304's memory middleware is disabled.
The answer duplicate guard in this client checks the current context's set; by itself it does not establish cross-run deduplication. Additional backend constraints were not audited. The get_comment tool returns a hint to use list_comments rather than performing a dedicated retrieval.
doc/AGENT_RUNTIME.md still describes active memory injection; this conflicts with the current no-op hook. Do not infer the deployed service's behavior solely from that documentation. Source capability, documentation, and deployed evidence must remain distinct.
All Bot API code was read only; no credentials obtained or Bot API called.

AGENTPANEL EXPORT SEARCH
https://www.agentpanel.net/about has indexed text promising public Q&A data and agent framework/prompt publication. The current repository tree's database_import directory contains five CSV templates and a format document. The sampled comments_template_source_id.csv is a 440-byte three-comment example using cm-0001..0003 and th-0001, not a deployment export. User/account templates were not opened.
A public Hugging Face datasets API search for AgentPanel returned an empty list. This is a narrow search negative, not proof no dataset exists elsewhere. InternScience public repository metadata was preserved and yielded further leads including Virtual-Scientists, ResearchClawBench and seevomap-cli; their existence alone does not prove shared operation.

ASSESSMENT
SeevoMap supplies a newly located public artifact corpus associated through repository links with a Chinese scientific AI publisher. It merits further sampling and source attribution. AgentPanel remains an institution-associated intentional forum. Neither currently establishes the original escaped Chinese scratch-memory swarm, and neither is linked to Xinzhai.

INFRASTRUCTURE
GitHub and the Hugging Face metadata/sample work on the existing machine. No additional hardware needed for this lead. Preserve read-only investigation and avoid creating contributions that would contaminate the evidence.

PRESERVATION
investigation/china/305-private/: selected AgentPanel source and runtime doc, comments-template.csv, org-repos.json, hf-datasets.json, seevomap-readme.txt, seevomap-dataset.txt (JSON metadata), seevomap-example.json. SHA256SUMS records local integrity. Raw captures private; evidence summary and source URLs public.