# Counterfactual Explanations on MNIST (test) Source: [Counterfactual Explanations on MNIST (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:46:52.174Z Evaluation of counterfactual explanation methods on the test split of the MNIST dataset, focusing on metrics such as IM1, Implausibility, Robustness Ratio, and Validity. 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 | Counterfactual Explanations | | Dataset (including any stated split) | MNIST (test) | | Metric | IM1 Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [IM1 Score](): Higher is better; unit: SCALAR. - [Implausibility](): Lower is better; unit: SCALAR. - [Robustness Ratio (1e-3)](): Higher is better; unit: PERCENT. - [Validity](): Higher is better; unit: PERCENT. ## Recorded results | Method | IM1 Score | Result date | Report paper | | --- | --- | --- | --- | | BayesCF | 1.6426 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | BayesCF | 1.6426 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | BayesCF | 1.6408 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | Wachter | 1.4984 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | ROAR | 1.4739 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | Schut | 1.2373 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | Schut | 1.2373 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | Schut | 1.2298 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | PSCE | 0.9768 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | PSCE | 0.9273 | Not recorded | 6976f4e9a2b28e761d87c0f0 | | PSCE | 0.9273 | Not recorded | 6976f4e9a2b28e761d87c0f0 | ### BayesCF IM1 Score: 1.6426. Result ID: 69991f7a5698665ec4866dd2. [Reporting paper]() Recorded evaluation configuration: {"Uncertainty Estimation":"MC Dropout"}. This record does not assert independent reproduction. ### BayesCF IM1 Score: 1.6426. Result ID: 69991f7a5698665ec4866de7. [Reporting paper]() Recorded evaluation configuration: {"Inference Method":"MC Dropout"}. This record does not assert independent reproduction. ### BayesCF IM1 Score: 1.6408. Result ID: 69991f7a5698665ec4866df6. [Reporting paper]() Recorded evaluation configuration: {"Model":"BNN"}. This record does not assert independent reproduction. ### Wachter IM1 Score: 1.4984. Result ID: 69991f7a5698665ec4866dd4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Estimation":"MC Dropout"}. This record does not assert independent reproduction. ### ROAR IM1 Score: 1.4739. Result ID: 69991f7a5698665ec4866dd5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Estimation":"MC Dropout"}. This record does not assert independent reproduction. ### Schut IM1 Score: 1.2373. Result ID: 69991f7a5698665ec4866dd3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Estimation":"MC Dropout"}. This record does not assert independent reproduction. ### Schut IM1 Score: 1.2373. Result ID: 69991f7a5698665ec4866de8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Method":"MC Dropout"}. This record does not assert independent reproduction. ### Schut IM1 Score: 1.2298. Result ID: 69991f7a5698665ec4866df7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"BNN"}. This record does not assert independent reproduction. ### PSCE IM1 Score: 0.9768. Result ID: 69991f7a5698665ec4866df5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"BNN"}. This record does not assert independent reproduction. ### PSCE IM1 Score: 0.9273. Result ID: 69991f7a5698665ec4866dd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Estimation":"MC Dropout"}. This record does not assert independent reproduction. ### PSCE IM1 Score: 0.9273. Result ID: 69991f7a5698665ec4866de6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Method":"MC Dropout"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.