# Image Classification on CIFAR-10 (test) (Error Bounds and KL Divergence) Source: [Image Classification on CIFAR-10 (test) (Error Bounds and KL Divergence)]() Collection index: [llms.txt]() Data updated: 2026-05-20T08:03:51.126Z Evaluation of Image Classification performance on the CIFAR-10 test set, reporting metrics related to model error bounds, test error, KL divergence, and prior test error. 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 | Error Bound | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 10 of 10 | | 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 - [Error Bound](): Lower is better; unit: SCALAR. - [Test Error](): Lower is better; unit: SCALAR. - [KL Divergence](): Lower is better; unit: SCALAR. - [Prior Test Error](): Lower is better; unit: SCALAR. ## Recorded results | Method | Error Bound | Result date | Report paper | | --- | --- | --- | --- | | CNNet9l (baseline) | 0.237 | Not recorded | 68fa70ee1e209131cea4e1ce | | CNNet9l (baseline) | 0.25 | Not recorded | 68fa70ee1e209131cea4e1ce | | GenFL | 0.345 | Not recorded | 68fa70ee1e209131cea4e1ce | | GenFL | 0.386 | Not recorded | 68fa70ee1e209131cea4e1ce | | GenFL | 0.393 | Not recorded | 68fa70ee1e209131cea4e1ce | | GenFL | 0.396 | Not recorded | 68fa70ee1e209131cea4e1ce | | GenFL | 0.458 | Not recorded | 68fa70ee1e209131cea4e1ce | | GenFL | 0.466 | Not recorded | 68fa70ee1e209131cea4e1ce | | GenFL | 0.469 | Not recorded | 68fa70ee1e209131cea4e1ce | | GenFL | 0.471 | Not recorded | 68fa70ee1e209131cea4e1ce | ### CNNet9l (baseline) Error Bound: 0.237. Result ID: 6a0d6aa0fbc373592c054d41. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet9l","Objective function (Obj.)":"f1","beta":"250","epsilon":"100","rounds":"\\"1\\"","Setting":"Batch"}. This record does not assert independent reproduction. ### CNNet9l (baseline) Error Bound: 0.25. Result ID: 6a0d6aa0fbc373592c054d42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet9l","Objective function (Obj.)":"f2","beta":"250","epsilon":"100","rounds":"\\"1\\"","Setting":"Batch"}. This record does not assert independent reproduction. ### GenFL Error Bound: 0.345. Result ID: 6a0d6aa0fbc373592c054d4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet9l","Objective function (Obj.)":"f2","beta":"5","epsilon":"1","rounds":"300","KL Penalty":"1.0","Number of users":"100"}. This record does not assert independent reproduction. ### GenFL Error Bound: 0.386. Result ID: 6a0d6aa0fbc373592c054d49. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet9l","Objective function (Obj.)":"f1","beta":"5","epsilon":"1","rounds":"300","KL Penalty":"1.0","Number of users":"100"}. This record does not assert independent reproduction. ### GenFL Error Bound: 0.393. Result ID: 6a0d6aa0fbc373592c054d45. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet9l","Objective function (Obj.)":"f1","beta":"5","epsilon":"1","rounds":"300","KL Penalty":"0.1","Number of users":"100"}. This record does not assert independent reproduction. ### GenFL Error Bound: 0.396. Result ID: 6a0d6aa0fbc373592c054d46. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet9l","Objective function (Obj.)":"f2","beta":"5","epsilon":"1","rounds":"300","KL Penalty":"0.1","Number of users":"100"}. This record does not assert independent reproduction. ### GenFL Error Bound: 0.458. Result ID: 6a0d6aa0fbc373592c054d48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet4l","Objective function (Obj.)":"f2","beta":"10","epsilon":"1","rounds":"300","KL Penalty":"1.0","Number of users":"100"}. This record does not assert independent reproduction. ### GenFL Error Bound: 0.466. Result ID: 6a0d6aa0fbc373592c054d47. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet4l","Objective function (Obj.)":"f1","beta":"10","epsilon":"1","rounds":"300","KL Penalty":"1.0","Number of users":"100"}. This record does not assert independent reproduction. ### GenFL Error Bound: 0.469. Result ID: 6a0d6aa0fbc373592c054d44. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet4l","Objective function (Obj.)":"f2","beta":"10","epsilon":"1","rounds":"300","KL Penalty":"0.1","Number of users":"100"}. This record does not assert independent reproduction. ### GenFL Error Bound: 0.471. Result ID: 6a0d6aa0fbc373592c054d43. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNNet4l","Objective function (Obj.)":"f1","beta":"10","epsilon":"1","rounds":"300","KL Penalty":"0.1","Number of users":"100"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.