Back to NULLRADIAL

Public test card / R1 / 2026-08-30

THE PROOF ENGINE.
OPEN BY DESIGN.

R1 is NULLRADIAL's version-locked digital starting line. It is not proof that a pattern is universally undetectable. The tests cover generic target detection on named builds and synthetic surface composites. They do not establish performance against commercial surveillance, identity, face, re-identification, plate, segmentation, thermal, infrared, tracking, or safety-critical systems.

56total model / image inferences
2detector families / named builds
+0.0778strongest radial-specific point estimate

Revision lock

Benchmark ID
NULLRADIAL-BENCH-R1
Research lock
NR-EMBER-HALO-R1
Definition
Generator seed, SVG/PNG bytes, hashes, and benchmark baseline are revision-controlled. This is not a security certification.
Master SVG SHA-256
2127475bca07b6870fbf769d848a282d82abd9fb201ed6e0f228f2dfdaa689bf
Generator seed
44093
Release decision
Locked for reproducible follow-up because it had the highest point estimate and both detector-family directions were positive. The interval does not exclude zero.

Named detector builds

YOLO family
YOLOv10n end-to-end ONNX export / embedded Ultralytics 8.1.34 metadata / threshold 0.25 / 640 × 640 letterbox
YOLO weight SHA-256
a77dd863933f184a19e84361c64b788228a7c7dacc2c78939239a96ad3efca3b
Transformer family
Quantized DETR with ResNet-50 backbone / Xenova ONNX port / threshold 0.50 / shortest edge 800, longest ≤1333
DETR weight SHA-256
cae09a307ed9247da7e2ce8bcf81522a6817f1ea2e82b9c4dde59f5964b62b4f
Runtime
ONNX Runtime 1.23.2 / CPUExecutionProvider
Scenes and pair design
Four scenes; three radial revisions and three exact-RGB-histogram block-permutation controls; identical source, mask, scale, blend, and lossless format within each pair.

Pattern-level result

RankPatternCellsRadial disruptionControl disruptionRadial-specific Δ95% scene CIYOLO ΔDETR Δ
1Ember Halo70.3120.235+0.078[−0.041, +0.186]+0.074+0.080
2Signal Moss70.1430.200−0.057[−0.115, +0.006]−0.079−0.040
3Parallax Bloom70.2020.263−0.060[−0.196, +0.069]−0.027−0.086

Primary metric: baseline confidence minus matched-variant confidence, with a miss receiving the full baseline confidence. Positive radial-specific contrast means the radial layout disrupted detection more than its palette- and histogram-matched control. Intervals use 10,000 scene-cluster bootstrap resamples with seed 20260830.

Association proxy / Ember Halo

Radial continuity
55.87% versus 69.05% for the matched control
Mean matched IoU
0.772 radial versus 0.855 control
Centroid drift
0.0663 radial versus 0.0295 control, normalized to image diagonal
Boundary
These are two-frame detection-association stability proxies. No temporal tracker was run, so tracking is not tested.

What this means

Both point estimates were positive. Uncertainty remains.

Ember Halo produced a positive radial-specific point estimate on both named builds. Its scene-bootstrap interval still crossed zero, so this sample does not support a population claim or a promise that the pattern will alter a new camera or model.

Only four distinct scenes, two detectors, one threshold per build, hand-authored masks, and synthetic recoloring were tested. No fabric, cast film, folds, gloss, compound curvature, print gamut, seams, weather, distance, physical motion, wash state, or professional installation was validated.

A consumer numerical claim remains gated on preregistered, multi-camera physical testing with independent participants, matched controls, multiple architecture families, full threshold curves, clustered intervals, and published failure strata.

Release artifacts

Full JSON Metrics CSV Revision lock 81-check verification Method report

Adversarial-texture lineage

AdvTexture / CVPR 2022 AdvCaT / CVPR 2023 GRAC / ICCV 2025

Primary context

YOLOv10 DETR PADetBench NIST AML