Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration

• URL: http://arxiv.org/abs/2609.01072v2
• Date: Wed, 02 Sep 2026 01:14:12 GMT
• Title: Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration
• Abstract summary: Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 prediction.<n>We propose Calibrator-Output Repair for Top-1 Decision Preservation (CORD), the first post-fit adapter to impose exact prediction preservation by repairing the full calibrated probability vector.
• Score: 4.300307544233363
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 prediction. Accuracy captures only the net effect of these changes on correctness, not how often predictions change; the Top-1 Prediction Change Rate (TPCR) instead measures this frequency. We propose Calibrator-Output Repair for Top-1 Decision Preservation (CORD), the first post-fit adapter to impose exact prediction preservation by repairing the full calibrated probability vector. From the original and calibrated outputs alone, CORD determines the mass assigned to the original top-1. The calibrated conditional distribution allocates the remaining mass over the other classes, yielding a repaired vector whose own argmax recovers the original prediction. On the calibration split, CORD coordinates the repaired masses to retain the calibrated outputs' mean mass on original predictions whenever attainable. The adapter alters neither the fitted calibrator nor its direct output, fits no additional supervised map, and requires no user- or validation-tuned hyperparameter. Across CIFAR-10/100 and ImageNet-1K, CORD attains zero TPCR by construction and lowers mean ECE, NLL, and Brier relative to the corresponding direct outputs in every dataset; paired gains persist under distribution shift and across calibration-set sizes. CORD thus removes the preservation constraint from calibrator fitting and assigns exact recovery of the original decision to subsequent output repair. Our code is available at https://github.com/labhai/CORD.

Related papers

• Rethinking Post-Hoc Calibration in Semantic Segmentation [2.8002121919083685]
  Post-hoc calibration offers a practical way to correct confidence estimates without retraining the segmentation model.<n>We study two such issues: first, adding a constant to all logits leaves the softmax probabilities unchanged, but several standard calibrators can still depend on this arbitrary offset.<n>Second, post-hoc calibration is typically fitted by minimizing a likelihood-based objective, whereas segmentation models are trained with task-specific metrics such as Dice.
  arXiv  Detail & Related papers  (2026-07-02T09:01:21Z)
• When Can We Reuse a Calibration Set for Multiple Conformal Predictions? [0.0]
  We show how e-conformal prediction, in conjunction with Hoeffding's inequality, can enable the repeated use of a single calibration set.<n>We train a deep neural network and utilise a calibration set to estimate a Hoeffding correction.<n>This correction allows us to apply a modified Markov's inequality, leading to the construction of prediction sets with quantifiable confidence.
  arXiv  Detail & Related papers  (2025-06-24T14:57:25Z)
• Adaptive Set-Mass Calibration with Conformal Prediction [60.47079469141295]
  We develop a new calibration procedure that starts with conformal prediction to obtain a set of labels that gives the desired coverage.<n>We then instantiate two simple post-hoc calibrators: a mass normalization and a temperature scaling-based rule, tuned to the conformal constraint.
  arXiv  Detail & Related papers  (2025-05-21T12:18:15Z)
• Calibrating Language Models with Adaptive Temperature Scaling [58.056023173579625]
  We introduce Adaptive Temperature Scaling (ATS), a post-hoc calibration method that predicts a temperature scaling parameter for each token prediction. ATS improves calibration by over 10-50% across three downstream natural language evaluation benchmarks compared to prior calibration methods.
  arXiv  Detail & Related papers  (2024-09-29T22:54:31Z)
• Towards Certification of Uncertainty Calibration under Adversarial Attacks [96.48317453951418]
  We show that attacks can significantly harm calibration, and thus propose certified calibration as worst-case bounds on calibration under adversarial perturbations.<n>We propose novel calibration attacks and demonstrate how they can improve model calibration through textitadversarial calibration training
  arXiv  Detail & Related papers  (2024-05-22T18:52:09Z)
• Optimizing Calibration by Gaining Aware of Prediction Correctness [30.619608580138802]
  Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class.<n>We propose a new post-hoc calibration objective derived from the aim of calibration.
  arXiv  Detail & Related papers  (2024-04-19T17:25:43Z)
• Calibration by Distribution Matching: Trainable Kernel Calibration Metrics [56.629245030893685]
  We introduce kernel-based calibration metrics that unify and generalize popular forms of calibration for both classification and regression. These metrics admit differentiable sample estimates, making it easy to incorporate a calibration objective into empirical risk minimization. We provide intuitive mechanisms to tailor calibration metrics to a decision task, and enforce accurate loss estimation and no regret decisions.
  arXiv  Detail & Related papers  (2023-10-31T06:19:40Z)
• Sample-dependent Adaptive Temperature Scaling for Improved Calibration [95.7477042886242]
  Post-hoc approach to compensate for neural networks being wrong is to perform temperature scaling. We propose to predict a different temperature value for each input, allowing us to adjust the mismatch between confidence and accuracy. We test our method on the ResNet50 and WideResNet28-10 architectures using the CIFAR10/100 and Tiny-ImageNet datasets.
  arXiv  Detail & Related papers  (2022-07-13T14:13:49Z)
• Revisiting Calibration for Question Answering [16.54743762235555]
  We argue that the traditional evaluation of calibration does not reflect usefulness of the model confidence. We propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence to wrong predictions and high confidence to correct predictions.
  arXiv  Detail & Related papers  (2022-05-25T05:49:56Z)
• Localized Calibration: Metrics and Recalibration [133.07044916594361]
  We propose a fine-grained calibration metric that spans the gap between fully global and fully individualized calibration. We then introduce a localized recalibration method, LoRe, that improves the LCE better than existing recalibration methods.
  arXiv  Detail & Related papers  (2021-02-22T07:22:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.