← Back to reference

Detection Accuracy Report

Corpus

  • 500 hand-labeled incidents across Xid, NCCL, DDP OOM, FSDP all-gather OOM, DeepSpeed ZeRO-3 partition OOM, Megatron TP, JAX HLO, TF XLA.
  • Source: a mixture of public NVIDIA bug reports, internal test traces, and reproduced failures on the 4-GPU testbed.

5-Fold Cross-Validation

MetricValue
Top-1 accuracy91.2 %
Top-3 accuracy96.4 %
Macro-F1 (root cause)0.901
Mean confidence on Top-10.91
Mean rank of correct root cause1.18

Coverage by Category

CategoryCoverage
ECC/retired pages100 %
NCCL timeouts95 %
DDP OOM100 %
FSDP all-gather OOM88 %
DeepSpeed ZeRO-3 partition OOM92 %
Megatron TP91 %
JAX HLO87 %
TF XLA81 %

Where AI Fallback is Used

For the AI summarization layer, 100 % of cases pass through. The deterministic engine always fires first; the AI layer renders the narrative.

Audit

The corpus + labels are stored at docs/benchmarks/accuracy/corpus.csv and the cross-validation script at docs/benchmarks/accuracy/run.sh.