# Calibration on CIFAR-10-LT (test) Source: [Calibration on CIFAR-10-LT (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:20.542Z Evaluation of model calibration performance on the test split of the CIFAR-10 dataset configured with a Long Tail (LT) class distribution, typically measured using ECE and MCE. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Calibration | | Dataset (including any stated split) | CIFAR-10-LT (test) | | Metric | ECE | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [ECE](): Lower is better; unit: PERCENT. - [MCE](): Lower is better; unit: PERCENT. ## Recorded results | Method | ECE | Result date | Report paper | | --- | --- | --- | --- | | UniMix+Bayias | 4.74 | Not recorded | 68fa6b331e209131cea2cd8f | | Bayias | 5.52 | Not recorded | 68fa6b331e209131cea2cd8f | | UniMix | 6 | Not recorded | 68fa6b331e209131cea2cd8f | | mixup | 6.55 | Not recorded | 68fa6b331e209131cea2cd8f | | ERM | 6.6 | Not recorded | 68fa6b331e209131cea2cd8f | | Remix | 6.81 | Not recorded | 68fa6b331e209131cea2cd8f | | UniMix+Bayias | 10.19 | Not recorded | 68fa6b331e209131cea2cd8f | | Bayias | 11.05 | Not recorded | 68fa6b331e209131cea2cd8f | | LDAM+DRW | 11.22 | Not recorded | 68fa6b331e209131cea2cd8f | | UniMix | 12.87 | Not recorded | 68fa6b331e209131cea2cd8f | | Remix | 15.38 | Not recorded | 68fa6b331e209131cea2cd8f | | mixup | 19.2 | Not recorded | 68fa6b331e209131cea2cd8f | | LDAM+DRW | 19.89 | Not recorded | 68fa6b331e209131cea2cd8f | | ERM | 20.53 | Not recorded | 68fa6b331e209131cea2cd8f | ### UniMix+Bayias ECE: 4.74. Result ID: 698e70d5ffc3901de09d9d77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"10"}. This record does not assert independent reproduction. ### Bayias ECE: 5.52. Result ID: 698e70d5ffc3901de09d9d75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"10"}. This record does not assert independent reproduction. ### UniMix ECE: 6. Result ID: 698e70d5ffc3901de09d9d73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"10"}. This record does not assert independent reproduction. ### mixup ECE: 6.55. Result ID: 698e70d5ffc3901de09d9d6d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"10"}. This record does not assert independent reproduction. ### ERM ECE: 6.6. Result ID: 698e70d5ffc3901de09d9d6b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"10"}. This record does not assert independent reproduction. ### Remix ECE: 6.81. Result ID: 698e70d5ffc3901de09d9d6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"10"}. This record does not assert independent reproduction. ### UniMix+Bayias ECE: 10.19. Result ID: 698e70d5ffc3901de09d9d78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"100"}. This record does not assert independent reproduction. ### Bayias ECE: 11.05. Result ID: 698e70d5ffc3901de09d9d76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"100"}. This record does not assert independent reproduction. ### LDAM+DRW ECE: 11.22. Result ID: 698e70d5ffc3901de09d9d71. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"10"}. This record does not assert independent reproduction. ### UniMix ECE: 12.87. Result ID: 698e70d5ffc3901de09d9d74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"100"}. This record does not assert independent reproduction. ### Remix ECE: 15.38. Result ID: 698e70d5ffc3901de09d9d70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"100"}. This record does not assert independent reproduction. ### mixup ECE: 19.2. Result ID: 698e70d5ffc3901de09d9d6e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"100"}. This record does not assert independent reproduction. ### LDAM+DRW ECE: 19.89. Result ID: 698e70d5ffc3901de09d9d72. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"100"}. This record does not assert independent reproduction. ### ERM ECE: 20.53. Result ID: 698e70d5ffc3901de09d9d6c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-32","Imbalance ratio (rho)":"100"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.