# Conformal Prediction on Camelyon (r\* ≤ 0.33) 17 (test) Source: [Conformal Prediction on Camelyon (r\* ≤ 0.33) 17 (test)]() Collection index: [llms.txt]() Data updated: 2026-06-16T07:01:15.462Z Evaluation of Conformal Prediction methods on the test split of the Camelyon 17 dataset, specifically constrained by the r\* ≤ 0.33 condition. Metrics reported include Coverage and Size. 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 | Conformal Prediction | | Dataset (including any stated split) | Camelyon (r\* ≤ 0.33) 17 (test) | | Metric | Coverage | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 30 of 30 | | 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 - [Coverage](): Higher is better; unit: PERCENT. - [Size](): Lower is better; unit: SCALAR. ## Recorded results | Method | Coverage | Result date | Report paper | | --- | --- | --- | --- | | Retrain | 91.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 89.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 89.3 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 88.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 87.9 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 87 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 86.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 85.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 85.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 85.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 83.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 83.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 78.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 76.3 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 74.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 74.5 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 71.4 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 64.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 63.6 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 40.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 36.2 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 30.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 28.9 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 27.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 27.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 25 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 24.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 22.2 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 19.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 17.9 | Not recorded | 6a30d896d33dfb23e783cc51 | ### Retrain Coverage: 91.1. Result ID: 6a30f4b7fbc373592c2ca2f2. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 89.7. Result ID: 6a30f4b7fbc373592c2ca2f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### Retrain Coverage: 89.3. Result ID: 6a30f4b7fbc373592c2ca2ec. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### Retrain Coverage: 88.8. Result ID: 6a30f4b7fbc373592c2ca2e6. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 87.9. Result ID: 6a30f4b7fbc373592c2ca2ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 87. Result ID: 6a30f4b7fbc373592c2ca2ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 86.1. Result ID: 6a30f4b7fbc373592c2ca2e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### Retrain Coverage: 85.8. Result ID: 6a30f4b7fbc373592c2ca2da. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 85.8. Result ID: 6a30f4b7fbc373592c2ca2ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 85.7. Result ID: 6a30f4b7fbc373592c2ca2dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"300"}. This record does not assert independent reproduction. ### Retrain Coverage: 83.7. Result ID: 6a30f4b7fbc373592c2ca2e0. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"300"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 83.7. Result ID: 6a30f4b7fbc373592c2ca2e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 78.8. Result ID: 6a30f4b7fbc373592c2ca2e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 76.3. Result ID: 6a30f4b7fbc373592c2ca2de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"300"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 74.8. Result ID: 6a30f4b7fbc373592c2ca2e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 74.5. Result ID: 6a30f4b7fbc373592c2ca2d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 71.4. Result ID: 6a30f4b7fbc373592c2ca2e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 64.7. Result ID: 6a30f4b7fbc373592c2ca2dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"300"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 63.6. Result ID: 6a30f4b7fbc373592c2ca2d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 40.7. Result ID: 6a30f4b7fbc373592c2ca2d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### AdaTS Coverage: 36.2. Result ID: 6a30f4b7fbc373592c2ca2df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"300"}. This record does not assert independent reproduction. ### AdaTS Coverage: 30.1. Result ID: 6a30f4b7fbc373592c2ca2eb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### AdaTS Coverage: 28.9. Result ID: 6a30f4b7fbc373592c2ca2f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### Standard Coverage: 27.8. Result ID: 6a30f4b7fbc373592c2ca2e1. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"300"}. This record does not assert independent reproduction. ### AdaTS Coverage: 27.1. Result ID: 6a30f4b7fbc373592c2ca2e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### AdaTS Coverage: 25. Result ID: 6a30f4b7fbc373592c2ca2d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### Standard Coverage: 24.1. Result ID: 6a30f4b7fbc373592c2ca2f3. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### Standard Coverage: 22.2. Result ID: 6a30f4b7fbc373592c2ca2ed. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### Standard Coverage: 19.7. Result ID: 6a30f4b7fbc373592c2ca2e7. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### Standard Coverage: 17.9. Result ID: 6a30f4b7fbc373592c2ca2db. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.