Failure Detection on Close Box Combined (train test)
100TPRTemporal Non-Distr. Min.
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Temporal Non-Distr. Min.Category=Diffusion2026.03 | 100 | 77 | 85 | |
| DDPM LossCategory=Diffusion2026.03 | 100 | 91 | 94 | |
| Temporal DDPM LossCategory=Diffusion2026.03 | 100 | 79 | 86 | |
| CLIP PretrainedCategory=Embed.2026.03 | 100 | 68 | 79 | |
| ResNet PretrainedCategory=Embed.2026.03 | 100 | 68 | 79 | |
| GPT-4o Image QACategory=VLM2026.03 | 100 | 0 | 29 | |
| Sentinel (STAC MMD* + GPT-4o Video QA*)Configuration=Parallel Ensemble2026.03 | 100 | 87 | 91 | |
| STAC For. KLCategory=STAC2026.03 | 99 | 89 | 92 | |
| STAC MMD*Category=STAC2026.03 | 99 | 94 | 96 | |
| Policy EncoderCategory=Embed.2026.03 | 94 | 70 | 78 | |
| STAC Rev. KLCategory=STAC2026.03 | 93 | 96 | 95 | |
| Temporal Diffusion Recon.Category=Diffusion2026.03 | 92 | 97 | 95 | |
| GPT-4o Video QA*Category=VLM2026.03 | 77 | 91 | 87 | |
| Diffusion Recon.Category=Diffusion2026.03 | 37 | 96 | 76 | |
| Diffusion Output VarianceCategory=Diffusion2026.03 | 26 | 96 | 72 |