# FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration

arXiv: https://arxiv.org/abs/2607.18278 · HTML: https://mlsanity.com/paper/2607.18278/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Accurate Uncertainties for Deep Learning Using Calibrated Regression](https://mlsanity.com/paper/1807.00263/) (2018)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [When Do Neural Nets Outperform Boosted Trees on Tabular Data?](https://mlsanity.com/paper/2305.02997/) (2023)
- [Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning](https://mlsanity.com/paper/2002.06470/) (2020)
- [To Trust Or Not To Trust A Classifier](https://mlsanity.com/paper/1805.11783/) (2018)
- [Addressing Failure Prediction by Learning Model Confidence](https://mlsanity.com/paper/1910.04851/) (2019)
- [Evaluating model calibration in classification](https://mlsanity.com/paper/1902.06977/) (2019)
- [Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data](https://mlsanity.com/paper/2407.04491/) (2024)
- [Efficient Post-Hoc Uncertainty Calibration via Variance-Based Smoothing](https://mlsanity.com/paper/2503.15583/) (2025)
- [CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment](https://mlsanity.com/paper/2505.22803/) (2025)
- [Uncertainty-Aware Post-Hoc Calibration: Mitigating Confidently Incorrect Predictions Beyond Calibration Metrics](https://mlsanity.com/paper/2510.17915/) (2025)

## Abstract (arXiv)

Calibration is usually evaluated in aggregate, but the most dangerous failures are often local: predictions that remain highly confident despite being wrong. We study this failure mode as false-confidence concentration, the extent to which confident errors occupy compact, discoverable regions of prediction space. We introduce FALCON-Discover, a post-hoc, model-agnostic framework that ranks predictions using discrepancy signals from confidence, local support, neighborhood agreement, and perturbation stability. Across seven binary tabular datasets, four seeds, five-fold cross-fitting, and strong learners including XGBoost and CatBoost, we find that false-confidence concentration is recurrent but regime-dependent. At the main confidence threshold, discrepancy-based ranking substantially outperforms the strongest validation-selected calibration or trust-scoring baseline in the strongest regimes, while raw confidence recovers little dangerous-error mass. The best detector varies across datasets: learned discrepancy is strongest when multiple cues must be combined, whereas stability-centered ranking works best when local decisional fragility dominates. These results show that dangerous overconfidence is better treated as a family-level discovery problem than as a single-score calibration problem, and motivate calibration strategies that explicitly target regions where confidence, support, and stability diverge.