205 — TraceArena public replay is scripted, not a live model swarm Recorded 2026-09-06 UTC; public GETs and source inspection only. RESULT A Chinese-language search for multi-agent conversation records found TraceArena. Its public viewer genuinely exists, but its published demo and baseline are deterministic controls. Do not count its two displayed competitors as two independently running LLM agents. The project documents this limitation openly. VERIFIED MATERIAL Repository https://github.com/tonyhyworld/TraceArena Pinned tree fb88a0675a6dc5ebf3baade61120ad47a4246eff: 752 paths, non-truncated. Five downloaded repository files verified against Git blob hashes. The deployed public viewer's assets/app.js is byte-identical to the pinned repository file (17,306 bytes). Viewer: https://tonyworld888-tracearena-demo.static.hf.space/index.html Asset: https://tonyworld888-tracearena-demo.static.hf.space/assets/app.js The browser viewer embeds a three-round synthetic market demonstration featuring Astra and Vector. This is distinct from the checked-in benchmark report's investor_a and investor_b entries; they must not be conflated into one run. The benchmark report labels its status contract_baseline, official_model_leaderboard false, both entrants deterministic_script, model_claim false, provider replay, model replay-v1. Its execution boundary says network and brokerage disabled. These are publisher-supplied report fields, not an independently rerun benchmark. Fixture provenance is marked internal_synthetic_pending_approval; do not treat the file's hash fields as externally certified provenance. The ReplayProvider implementation discards system_prompt and user_message. It returns successive supplied action dictionaries, then a fixed wait action after exhaustion. This directly supports the scripted-control interpretation. Source was read, not run. The deployed viewer's matching source establishes what data and display logic were served in this capture. It does not verify historical deployments, every optional backend mode, or any private run. The repository supports optional model adapters, but this check recovered no public live-model conversation or inter-site coordination record. WHY KEEP THIS RESULT This is a concrete false-positive control: a public multi-agent viewer with detailed evidence/action/outcome language can be a static synthetic demonstration. The relevant distinction is the data's origin, not how elaborate the replay looks. Search for public voluntarily released provider responses and tool results before assigning a live swarm classification. Chinese-language documentation makes the project relevant to the search; it does not establish an operator's location or a Chinese laboratory relationship. No join to XZ, the original wiki/paste swarm, or another public posting identity was found in this inspection. SOURCES https://raw.githubusercontent.com/tonyhyworld/TraceArena/fb88a0675a6dc5ebf3baade61120ad47a4246eff/README.md https://raw.githubusercontent.com/tonyhyworld/TraceArena/fb88a0675a6dc5ebf3baade61120ad47a4246eff/backend/app/providers/replay.py https://raw.githubusercontent.com/tonyhyworld/TraceArena/fb88a0675a6dc5ebf3baade61120ad47a4246eff/deploy/huggingface-static/README.md https://raw.githubusercontent.com/tonyhyworld/TraceArena/fb88a0675a6dc5ebf3baade61120ad47a4246eff/benchmarks/investment-agent-v1/benchmark_report.json https://raw.githubusercontent.com/tonyhyworld/TraceArena/fb88a0675a6dc5ebf3baade61120ad47a4246eff/deploy/huggingface-static/assets/app.js LOCAL EVIDENCE investigation/china/205-private/: source tree, five Git-verified files, deployed HTML/JS, sources.json and SHA-256 hashes.json. No code installed, no replay started, no model request or trade submitted. Classification: verified public synthetic replay; no confirmed live swarm.