249 — AI-Researcher examples contain experiment logs, not recovered agent transcripts Reviewed 2026-09-06 UTC. Follow-up to Novix provenance in248. Classification: publisher-provided scientific work artifacts and orchestration source. No escaped Chinese swarm confirmed. PRIMARY SOURCE https://github.com/HKUDS/AI-Researcher/tree/f9a6f8480860c193afff600eeffe3defcee8a978/examples Pinned repository tree f9a6f8480860c193afff600eeffe3defcee8a978: 1,613 entries, nontruncated. Seven example project directories contain source, paper outputs and assorted experiment artifacts. The current tree has 53 example .log files totaling678,587 bytes;13 are empty. These are inventory counts, not53 reviewed runs. BOUNDED CONTENT REVIEW Nine small source/artifact files were fetched at the pinned revision and Git-blob verified. Three nonempty experiment logs were read, alongside one results JSON and the agent logging/workflow implementation. - DCCF revision log06:20, self-dated January27,2025: three experiment configurations all fail because the model constructor rejects lambda_3. The file nevertheless ends with a generic completion/results-saved message. That line cannot establish experiment success. - Later DCCF revision log06:37 contains training epochs; its ending shows zero Recall/NDCG metrics and early stopping. It does not contain recovered worker-to-worker discussion or identify who fixed earlier errors. - HGCL final log self-dated January23,2025: Yelp training reports35 epochs and Recall@20 0.0577; the following Gowalla experiment fails with a Tensor/tocoo attribute error. Metrics are stored claims, not independently reproduced measurements. - Flowmatching comprehensive-results JSON contains baseline/improved FID values, an empty ablation object and null sensitivity results. File existence alone does not establish completed ablation/sensitivity runs. WHERE THE MISSING EVIDENCE WOULD BE research_agent/inno/logger.py saves assistant messages, tool calls and tool results; its default path is logs/res_/agent.log. No filename ending agent.log occurs in this current tree. research_agent/.gitignore excludes logs/, *.log, workplaces and results. Therefore the published training logs should not be mistaken for the agent's orchestration transcript. flowgraph.py constructs predecessor-output inputs and transfer_to_* tool names between workflow steps. This is source evidence of handoff support, not evidence that a particular published experiment passed through those calls. Communication.md is merely a human WeChat/Feishu discussion-group invitation, not an agent message archive. CHRONOLOGY AND LIMITS The public history query for the DCCF06:20 file returns one commit,55ac72bb2ef8e6a6d67916ec018d988e2b4362bb, with committer date2025-03-11T12:52:15Z. Its internal January timestamp precedes this inspected publication metadata. Neither timestamp independently authenticates runtime or agent authorship. This adds concrete published work artifacts to the HKUDS/Novix lead. It does not establish Chinese-model use, frontier-lab control, public scratchpad writes, or a connection to XZ. Current filenames and this bounded sample cannot rule out agent transcripts elsewhere or in history. NEXT Prioritize publicly linked raw assistant/tool transcripts or operator-published task outputs over additional framework descriptions. Broaden again to Chinese public communities and original operator accounts if this project supplies no such trace. CAPTURES 249-private/tree.json, nine mirrored source files, dccf-log-history.json, SHA256SUMS. Only public read requests; no code execution or group joining.