Supervised Pairwise Graph Representations
Supervised pairwise graph representations convert pairwise predictive relations into sample-specific graphs, but graph-level accuracy does not by itself show that higher-order topology carries the signal.
Controlled Transformer Error-Detection Task
In a controlled Transformer error-detection task, supervised pairwise graphs outperform attention-as-adjacency (ROC-AUC $0.839$ versus $0.559$; the comparable no-confidence pair is $0.687$ versus $0.559$), but their apparent advantage over model confidence disappears after controlling for sequence length, which is almost perfectly recoverable from the pooled hidden state ($R^2=0.9995$).
Published HCP Emotion Ensemble Graphs
- On published HCP Emotion ensemble graphs, signed node aggregation already acts as an ensemble of supervised pairwise predictions.
- Edge magnitude alone is near chance; topology-aware augmentations change ROC-AUC by at most $0.004$, with only sign-separated degree showing small positive changes across all tested graph sizes, while a validation-tuned three-layer GCN provides no measurable improvement over the signed node-summary baseline.
Fisher Post-Hoc Corrector and fMRI Calibration
- A Fisher post-hoc corrector satisfies its distribution-agnostic guarantees across the evaluated feature representations and remains