# Image Classification on CIFAR-10 (test) (NLL, JS-Distance, ECE) Source: [Image Classification on CIFAR-10 (test) (NLL, JS-Distance, ECE)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:53:13.898Z Evaluation of Image Classification performance on the CIFAR-10 test set, focusing on calibration and uncertainty metrics, specifically Negative Log-Likelihood (NLL), Jensen-Shannon Distance (JS-Distance), and Expected Calibration Error (ECE). 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 | Image Classification | | Dataset (including any stated split) | CIFAR-10 (test) | | Metric | NLL | | Unit | SCALAR | | 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 - [NLL](): Lower is better; unit: SCALAR. - [JS-Distance](): Lower is better; unit: SCALAR. - [ECE](): Lower is better; unit: PERCENT. ## Recorded results | Method | NLL | Result date | Report paper | | --- | --- | --- | --- | | DNN\_dense | 0.2042 | Not recorded | 68fa6b611e209131cea2de52 | | BNN\_average | 0.2116 | Not recorded | 68fa6b611e209131cea2de52 | | BNN\_anneal | 0.2218 | Not recorded | 68fa6b611e209131cea2de52 | | DNN\_dense | 0.2276 | Not recorded | 68fa6b611e209131cea2de52 | | BNN\_average | 0.2323 | Not recorded | 68fa6b611e209131cea2de52 | | BNN\_anneal | 0.2441 | Not recorded | 68fa6b611e209131cea2de52 | | BNN\_average | 0.2528 | Not recorded | 68fa6b611e209131cea2de52 | | BNN\_average | 0.2587 | Not recorded | 68fa6b611e209131cea2de52 | | BNN\_anneal | 0.2618 | Not recorded | 68fa6b611e209131cea2de52 | | BNN\_anneal | 0.2676 | Not recorded | 68fa6b611e209131cea2de52 | | DPF | 0.2677 | Not recorded | 68fa6b611e209131cea2de52 | | DPF | 0.2833 | Not recorded | 68fa6b611e209131cea2de52 | | DPF | 0.2874 | Not recorded | 68fa6b611e209131cea2de52 | | DPF | 0.2921 | Not recorded | 68fa6b611e209131cea2de52 | ### DNN\_dense NLL: 0.2042. Result ID: 698e83b9ffc3901de09e3ef2. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet32","Pruning Ratio":"100%"}. This record does not assert independent reproduction. ### BNN\_average NLL: 0.2116. Result ID: 698e83b9ffc3901de09e3ef3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet32","Pruning Ratio":"9.99%"}. This record does not assert independent reproduction. ### BNN\_anneal NLL: 0.2218. Result ID: 698e83b9ffc3901de09e3ef4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet32","Pruning Ratio":"9.97%"}. This record does not assert independent reproduction. ### DNN\_dense NLL: 0.2276. Result ID: 698e83b9ffc3901de09e3eeb. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet20","Pruning Ratio":"100%"}. This record does not assert independent reproduction. ### BNN\_average NLL: 0.2323. Result ID: 698e83b9ffc3901de09e3eef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet20","Pruning Ratio":"19.85%"}. This record does not assert independent reproduction. ### BNN\_anneal NLL: 0.2441. Result ID: 698e83b9ffc3901de09e3ef0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet20","Pruning Ratio":"19.80%"}. This record does not assert independent reproduction. ### BNN\_average NLL: 0.2528. Result ID: 698e83b9ffc3901de09e3eec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet20","Pruning Ratio":"9.88%"}. This record does not assert independent reproduction. ### BNN\_average NLL: 0.2587. Result ID: 698e83b9ffc3901de09e3ef6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet32","Pruning Ratio":"4.77%"}. This record does not assert independent reproduction. ### BNN\_anneal NLL: 0.2618. Result ID: 698e83b9ffc3901de09e3eed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet20","Pruning Ratio":"9.95%"}. This record does not assert independent reproduction. ### BNN\_anneal NLL: 0.2676. Result ID: 698e83b9ffc3901de09e3ef7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ResNet32","Pruning Ratio":"4.88%"}. This record does not assert independent reproduction. ### DPF NLL: 0.2677. Result ID: 698e83b9ffc3901de09e3ef5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet32","Pruning Ratio":"10%"}. This record does not assert independent reproduction. ### DPF NLL: 0.2833. Result ID: 698e83b9ffc3901de09e3eee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet20","Pruning Ratio":"10%"}. This record does not assert independent reproduction. ### DPF NLL: 0.2874. Result ID: 698e83b9ffc3901de09e3ef1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet20","Pruning Ratio":"20%"}. This record does not assert independent reproduction. ### DPF NLL: 0.2921. Result ID: 698e83b9ffc3901de09e3ef8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet32","Pruning Ratio":"5%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.