AutoResearch task claims and EvoMap experiment boundaries Reviewed September 6, 2026 UTC. Public source and publisher-page inspection. RESULT AutoResearch contains a concrete local task-claim mechanism. Public documentation explicitly says runtime outputs are not distributed with the repository, and the releases endpoint returned an empty list. This resolves the current-tree absence more strongly than filename searches alone. The separate EvoX swarm article provides useful experimental qualifications, but does not supply the missing production agent conversation archive. PINNED RUNTIME SOURCES https://github.com/EvoMap/AutoResearch/blob/6b85443f9e3d33d357c86c8bb826f9ea03c780b3/ARCHITECTURE.md Architecture explicitly limits the repository to source, templates and synthetic examples; data/logs/runtime state are local outputs. It describes research collection from both Chinese and international sources, a recoverable queue, and a separate supervisor. These are intended operation details, not observed executions. https://github.com/EvoMap/AutoResearch/blob/6b85443f9e3d33d357c86c8bb826f9ea03c780b3/ar-runtime/ar-coordinator-startup-flow.md Startup documentation describes planner, coder and runner roles, a coordinator updating persistent queue/state, and automatic continuation. Target instructions were read as evidence and not followed. https://github.com/EvoMap/AutoResearch/blob/6b85443f9e3d33d357c86c8bb826f9ea03c780b3/ar-runtime/scripts/ar-workflow-engine.py Downloaded161,982 bytes. queue_lock uses fcntl.flock on workflow_queue.lock. command_claim locks the read/reclaim/select/write sequence, chooses the first ready unit, records claimed_by, claim_attempts and lease_expires_at, and appends a unit_claimed decision. Expired leases return work to pending or block it after the retry threshold. This supports local workers coordinating through a shared queue; it does not imply geographically separate agents or public Internet memory. No concurrency test or target execution was performed. No end-to-end correctness claim is made. RELEASE AND PUBLIC OUTPUT CHECK https://api.github.com/repos/EvoMap/AutoResearch/releases HTTP200, [] at capture time. No release asset bundle was available through this endpoint. https://evomap.ai/research/autoresearch-evidence-loop HTTP200. The publisher describes a Django repair progressing from2/7 to7/7 new-feature tests with203/203 regression tests, plus Kaggle cases. It warns the compared conditions had different time and feedback access. The extracted HTML links did not provide a run archive. Its Django PR link is the reference task/fix, not proof that AutoResearch authored that PR. No independent operator execution was found in this bounded search; promotional reposts repeat publisher claims. SEPARATE EVOX SWARM EXPERIMENT https://evomap.ai/research/self-organizing-ai-swarms HTTP200, preserved HTML/text. The publisher's July27 article compares scripted per-question decomposition/programmatic aggregation with lead-agent and single-context approaches. Reported accuracies are70.69-70.87%,38.54%,26.29%, with563 questions as denominator and one swarm network timeout. These are author-reported measurements, not reproduced results. Crucially, the article says the first experiment does not close autonomous decomposition/task-claiming/communication. Its second experiment's network edges denote partner reconnection choices, not messages or task handoffs; actual collaboration over those connections remains future validation. Do not count a rendered network as a captured communicating swarm or infer self-organization from the accuracy headline. CONTEXT AND DEDUPLICATION EvoMap as a platform was already investigated in reports228-233. Council histories and public welfare-project outputs are separate records; no join to AutoResearch runs is established. Report233 found LongWoF's release excludes raw agent traces. AutoResearch is a new project-specific branch of an existing operator lead, not a newly discovered platform. SeevoMap is separately investigated and not joined by name similarity. NEXT SEARCH Follow other public operator exports and Chinese discussion communities. AutoResearch's formal output filenames are useful exact-string search leads, but absence from search is not proof no deployment exists. A voluntarily published workflow_events.jsonl plus associated code/results would be more informative than another product summary. Current sources work from this server; no new infrastructure required for this branch. PRESERVATION 313-private: releases.raw, architecture.raw, startup.raw, engine.raw, research/loop/swarm HTML and extracted text/link lists; SHA256SUMS and publication-check.json. No credentials, registration, task claims, model requests or target execution. Raw captures remain private.