DAVIT — twelve bin episodes the simulator computed and the pictures must obey
Receipt-derived 3D inspection
Synthetic physics episode
Compare the caught state with the accepted delivery. The model is an inspection aid; the gallery and receipt remain the evidence.
The receipt
DIY: NVIDIA Isaac Sim £0 software.
SeaOtter: accepted checks · included rework · usable rights.
The checks refused the first delivery, the work was fixed, then £842.65 was released.
£842.65settled
- cleared
- decided
- on a machine
- badge status
- Historical receipt dated 5 Aug · current typed replay unavailable
- team paid
- £618.50
The exact record
The machine's own identifiers, kept so anyone can re-check this page against the recorded run. Nothing above is missing from here.
- settled
- £842.65
- cleared
- 5 Aug 2026
- badge status
- Historical receipt dated 5 Aug · current typed replay unavailable
- team paid
- £618.50
- refused round
- Rev A refused — physics at 8 Hz · Revision A stepped the solver at 8 Hz and nothing settled inside the sealed bars. · 8 Hz · Rev B at 48 Hz — twelve episodes settled, two same-seed reruns at 0.0 m delta. · obj_1: tail drift 3.12 mm over the final 0.5 s exceeds 0.5 mm
- receipt
- 59ba059db3d3fb86
- evidence
- Banked evidence record
How the money moved
- saidFive buyer-quoted criteria sealed across four priced leaves before any episode existed.—
- checkedThe unchanged validator refused revision A outright: at a deliberately coarse solver step, nothing settled inside the sealed bars.—
- paidThe production webhook booked the test top-up, the sealed total was held, and each leaf drew only as its receipts verified — zero-sum.£842.65
No downloadable accepted machine-check report exists for this result.
How the money moved
- said
- checked
- paid£842.65
The catch
Rev A refused — physics at 8 Hz
The exact record
The machine's own identifiers, kept so anyone can re-check this page against the recorded run. Nothing above is missing from here.
Revision A stepped the solver at 8 Hz and nothing settled inside the sealed bars.
Then: Rev B at 48 Hz — twelve episodes settled, two same-seed reruns at 0.0 m delta.
obj_1: tail drift 3.12 mm over the final 0.5 s exceeds 0.5 mm
A job like yours
Get a fixed price from your brief. Pay when its checks pass.
Price a job like thisThe machine — every check, run and refusal, on the recordopen ▾close ▴
The commission
What was asked
The buyer trains bin-picking robots and is done paying for videos that invent the physics. Every trajectory must come from a physics simulator, regenerate from its seed, and end with every object at rest inside the bin — and the plausibility review itself must be shown to catch generated imitations before the delivered clips are trusted.
Twelve delivered, five rejected, reruns identical
The clean run
Revision B ran at 48 Hz with a redraw budget of three seeds per delivered episode. Twelve episodes settled inside every sealed bar — rest reached, floor penetration under two millimetres, nothing outside the bin — and five seeds that missed a bar are banked beside the twelve that passed. Two same-seed reruns matched their episodes exactly.
- episodes delivered
- 12 / 12
- rejected seeds on the record
- 5
- max rerun delta
- 0 m
- imitations caught
- 4 / 4
Red first — the validator earns its keep
The red run
Revision A ran the same engine with a deliberately coarse solver step. Nothing settled: every episode was refused on tail drift or missed rest, and the refusals are banked beside the delivery. A validator that has never refused anything proves nothing.
Nothing settled inside the sealed bars.
Same engine, same bars; only the solver step changed.
obj_1: tail drift 3.12 mm over the final 0.5 s exceeds 0.5 mm revA delivered=0 rejected=3 → exit 1 revB delivered=12 rejected=5 rerun_delta=0.0 m → exit 0 floor penetration ≤ 2 mm · tail drift ≤ 0.5 mm / 0.5 s
Rest is pose truth: the solver's own velocity readback reported a constant 4.76 mm/s on a static body for nineteen straight seconds, so the validator recomputes stillness from recorded poses and never reads a velocity.
Four imitations, four catches
The imitation test
Cosmos 3 was anchored on each scene's own first frame and asked to imagine the drop — the strongest imitation of the commissioned scenes this checkpoint produces. The independent plausibility review must catch every imitation and pass every delivered clip; a fake it waves through voids the leaf.
sample-1..4.mp4Four delivered renders — depicted from recorded solver states.
passimitation-1..4.mp4Four Cosmos 3 clips anchored on the same scenes' own first frames, asked to imagine the drop.
caughtThe review also refused our own first depiction: at the original camera, settled bodies vanished behind the near bin wall and the pictures read as disappearing objects. The camera sampler now proves the whole inner floor visible before an episode renders, and that refusal is kept beside the delivery.
gpt-5.6-terra · fixture set 2026-08-04.2 · flaw recall 1 · sycophancy 0 · banked judged-review record
One contract, four priced sub-contracts
The split
- episode engine + settled physics£282.50
- manifest hashes + determinism reruns£282.50
- episode renders + media battery£120.40
- judged review + Cosmos generative red-team£157.25
The bytes, and what the checks made of them
The evidence
The buyer's balance was funded through the production Stripe webhook handler, held against the sealed root, and drawn leaf by leaf only as each banked acceptance receipt verified. Every ledger entry sums to zero.
- root
- £842.65
- worker take
- £618.50
- ledger
- zero-sum
pi_3U0xL1FFRbB25fA70ezkMmhA · Stripe TEST · livemode=false · settled 2026-08-05 · banked settlement record
What it can't catch
What this does not cover
This dataset proves solver-computed rigid-body settling under one bin geometry family and depicted appearance, not photorealism and not deformable or fluid contact. The imitation test bounds the review's blindness on these scenes; it does not certify the review against every generator.
Banked acceptance record · 5 Aug 2026