242 — ARIS Movie Director: structured review records and explicit human override
Reviewed September 6, 2026 UTC.

RESULT
A Chinese-documented visual-generation project publishes structured attempt/review/decision records, with Chinese reviewer notes and associated image paths. This is a more concrete artifact trail than generic social posts. Its inspected records do not independently authenticate provider calls, reviewer isolation, or an unattended run, and establish no Chinese-lab swarm attribution.

PINNED SOURCE
https://github.com/wanshuiyin/ARIS-Movie-Director
Revision 6e8665adfae91621cc1cb239e4149f374d04d110; nontruncated recursive tree contains 522 entries. The reference wiki nodes directory contains 198 files, matching the documented total. Six files were fetched at that revision and verified against Git blob hashes: wiki README, S01 attempt a01, Gemini and Codex review nodes for that attempt, its decision, and the B03 human-override decision. Other nodes were not exhaustively read.

CONCRETE SAMPLE
The attempt identifies panels/S01_panel_a01.png, which exists in the tree. The image itself was not downloaded or visually assessed in this pass.
The Gemini-labelled record transcribes dllm-schema-keyword-first. The Codex-labelled record instead transcribes dilm-schema-keyword-first and sets content_corruption_present=true. The linked decision returns retry_panel and requests a spelling repair. This is an internally linked published disagreement/retry record, not independent validation of the pixels or actual model calls.
The Codex review notes explicitly discuss agreement/disagreement with Gemini. Accordingly, this stored node alone cannot establish that the underlying review was blind or isolated; it may include subsequent comparison or annotation. That provenance question remains unresolved.

DISCLOSED LIMITS
The wiki README says created_at values are logical placeholders, not wall-clock timestamps. Identical June 8 midnight values in the sampled nodes must not be used to calculate concurrency, response time or execution date.
The B03 decision uses verdict=accept_by_human and explains that a cross-frame cast comparison caused a false rejection. It records human inspection and acceptance. Thus this published run includes human intervention; do not summarize it as fully unattended.
The source's assertion that the trace is authentic is a publisher claim. Git blob verification authenticates the retrieved repository content, not the history of its generation or named provider identities. Chinese documentation and notes also do not establish a Chinese lab operator.

WHY THIS LEAD IS USEFUL
It gives explicit attempt IDs, review targets, decisions and image paths, enabling artifact-level checks in a future pass. The next useful step is to inspect the linked image, trace provenance and any raw review output, while distinguishing production records from demonstration fixtures. Do not run the investigated pipeline or purchase generation calls.
Discovery came from Chinese overnight/multi-agent searches. Another separate unreviewed operator-demo lead is https://forum.trae.cn/t/topic/116011 (Polynoia AgentHub), which advertises a shared workspace and inline diffs; its deployment and runtime claims are not yet reviewed.

CAPTURES
242-private/tree.json, six pinned source records and SHA256SUMS. No code executed, images generated, model calls launched or private logs sought. No independently confirmed swarm.

FOLLOW-UP: Report 243 finds a version mismatch between the current S01 a01 review and its named image. Git history shows the review changed during a later re-bake while the image path retains an earlier artifact. Do not treat the current relative-path join as a verified review of those pixels.