247 — ClawTeam research claim: seven named optimization commits resolve
Reviewed 2026-09-06 UTC. Classification: published research artifacts; runtime and Chinese-lab attribution unresolved. No escaped swarm confirmed.

PROVENANCE
The Chinese-documented win4r/ClawTeam-OpenClaw adaptation points upstream to HKUDS/ClawTeam. Upstream links its eight-agent experiment example to novix-science/autoresearch. Do not count the adaptation as a second independent experiment.
https://github.com/win4r/ClawTeam-OpenClaw
https://github.com/HKUDS/ClawTeam
https://github.com/novix-science/autoresearch

CLAIM AND LIMIT
The results README describes four Claude Code and four Codex workers, with the latter replaced later, and 2,430+ experiments. It reports approximately 240 GPU-hours, whereas upstream ClawTeam says approximately 30 GPU-hours. These disagree; eight GPUs for 30 hours would account for 240 GPU-hours. Provider labels are publisher descriptions, not authenticated backend identities.

DIRECT ARTIFACT CHECK
Pinned results tree: 29a5846ba40f25c24ce316c50fe99e376d1dff8f, 13 entries, nontruncated. README.md, results_summary.tsv, .gitignore and plot_progress.py were fetched at that revision and verified against Git blob hashes.
The TSV contains eight per-agent rows, not the full experiment history. Seven of its eight abbreviated commit identifiers resolve through GitHub's public commit API; each returned a train.py change and a March 15, 2026 committer timestamp. Identifier 971d4ee returned HTTP422. That is a bounded retrieval failure, not proof the experiment was fabricated. Detailed identifiers and statuses: 247-private/commit-checks.json.
The current default-branch history returned 47 commits, ending March15. Commit timestamps are publisher-controlled metadata, not independent proof of execution on those dates.
.gitignore excludes results.tsv, results/, queue/ and worktrees/. No complete raw worker message archive or 2,430-row experiment log is present in this current 13-entry tree. Historical branches and deleted artifacts have not been exhaustively checked.

ASSESSMENT
This is stronger than an unlinked demonstration claim: seven named outputs have concrete source-change counterparts. It does not authenticate autonomous authorship, measured scores, uninterrupted operation or Chinese-lab ownership. It does not show public scratch-memory use or connect to XZ. Next useful checks: branch inventory, retained result-file history, and public operator provenance.

CAPTURES
investigation/china/247-private/ contains tree responses, four verified source files, commit history and eight commit lookups; SHA256SUMS inventories captures. No investigated software executed.