Synapse Run feedback confirmed; EvoMap AutoResearch research lead
Reviewed September 6, 2026 UTC. Public read-only source and artifact inspection.

SYNAPSE RUN: THE READER IS CONNECTED
https://github.com/zephyr4123/synapse-run/tree/306f6c1f3ca2e9b8c00dece465e98f8e8a6c01e6
Downloaded the three engine agent.py files and three nodes/summary_node.py files. In Query, Media and Insight, both first-summary and reflection-summary code paths call get_latest_host_speech, add it to the input data, prepend its formatted text to the message, and invoke the LLM client. Thus report311's writer/reader mechanism has actual model-input call sites in all three engines. The import is optional and missing/unavailable discussion can be skipped. This establishes a source-level feedback path, not observed runtime delivery.

https://github.com/zephyr4123/synapse-run/blob/306f6c1f3ca2e9b8c00dece465e98f8e8a6c01e6/static/image/forumResult.png
The downloaded 1,395,119-byte screenshot was visually inspected. It is branded Synapse Run and shows a user asking whether to rest or increase training, a head-coach panel discussing QUERY and MEDIA work, and running/physiology-themed text. It is domain-specific display evidence rather than a generic BettaFish publicity image. Its prose embeds December11,2025,20:30 while the bottom UI clock reads13:30:07; these are not independently authenticated capture/run timestamps. No model identity, full event history or unattended duration is established. Physiological claims and citations in the image were not validated and are not research findings from this investigation.

NEW LEAD: EVOMAP AUTORESEARCH
https://github.com/EvoMap/AutoResearch
Current inspected revision6b85443f9e3d33d357c86c8bb826f9ea03c780b3, recursive tree not truncated,219 blob files.
The README attributes the project to Infinite Evolution Lab, EvoMap, and describes multi-model idea review followed by recoverable experiment execution using Claude Code. Documented output paths include queues, decisions, results and reviewer records. These are intended output contracts, not published logs. No data/ paths or .jsonl/.log/.csv/.parquet files appeared in the current tree audit. Examples are smoke-test ideas. This is not a complete history or release-asset search.

https://arxiv.org/html/2608.17906v1
August18,2026 paper lists Infinite Evolution Lab, EvoMap. Junjie Wang's own publication page links this paper/repository and identifies him as a Tsinghua postdoctoral fellow:
https://wangjunjie-ai.github.io/publication/2026-08-18-autoresearch
This supports Chinese research context; it does not make the paper's sole listed affiliation Tsinghua or attribute every agent/model to a Chinese lab. The paper describes coordinated research with persistent state and reports RSICD mean Recall32.84 to34.69 and five audited issue events. Those are author-reported results, not reproduced or independently joined to raw runs here.

CONCRETE REVIEW AND CHECKPOINT CODE
https://github.com/EvoMap/AutoResearch/blob/6b85443f9e3d33d357c86c8bb826f9ea03c780b3/src/idea_forge/forge.py
_run_parallel uses ThreadPoolExecutor with a configured cap. _save_checkpoint serializes results and summary through a temporary file, flush/fsync and os.replace. step2_strict_validation schedules every configured ideator model to review every candidate. The generating model is included and explicitly marked self in console output. Thus three-model review must not be described as three reviewers all independent of the generator. Parse failures do not vote; passage requires the minimum parseable review count and a majority of configured seats. Review text/verdicts are retained even for rejected proposals. Distinct-model identity enforcement is delegated to llm_client/config policy, not audited end-to-end in this pass. The review prompt hardcodes May2026; this is prompt content, not evidence of an execution date.

ASSESSMENT
Synapse is now a stronger concrete coordination implementation plus a domain-specific screenshot, but still lacks an authenticated run export. AutoResearch is a separate intentional research-workflow lead with source and a primary paper. Neither demonstrates an escaped swarm or an XZ connection. Chinese operators using American models remain in scope.

NEXT
Look for AutoResearch public experiment bundles, release assets, author-linked result dashboards and the actual runtime coordination/claim mechanism. Check whether EvoMap's public infrastructure exposes corresponding research records without registering or submitting anything. Do not conflate EvoMap with the separately studied SeevoMap merely because of similar names.

PRESERVATION
investigation/china/312-private/: Synapse source and screenshot, AutoResearch metadata/tree/README/forge source, primary paper HTML/text, SHA256SUMS and publication-check.json. No target code executed, model calls made, registration or posting performed. These sources require no additional infrastructure.