# Conformal Prediction on 5-class synthetic data Hard Bin, r\* \<= 0.5 Source: [Conformal Prediction on 5-class synthetic data Hard Bin, r\* \<= 0.5]() Collection index: [llms.txt]() Data updated: 2026-06-16T07:01:15.191Z Evaluation of Conformal Prediction performance on the 5-class synthetic dataset variant characterized by the hard binning condition (r\* \<= 0.5). Metrics evaluated include Coverage and Average Set 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) | 5-class synthetic data Hard Bin, r\* \<= 0.5 | | 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. - [Average Set Size](): Lower is better; unit: SCALAR. ## Recorded results | Method | Coverage | Result date | Report paper | | --- | --- | --- | --- | | ACP-ACC | 92.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 91.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 91.3 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 90.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 90.2 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 87 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 86.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 84.9 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 84.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 84 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 81.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 77.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-ACC | 74.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 73.2 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 70 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 69.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 68.7 | Not recorded | 6a30d896d33dfb23e783cc51 | | Retrain | 67.6 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-MC | 66.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | ACP-AEC | 56.2 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 48.4 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 46.5 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 46.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 45.5 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 45.4 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 45.1 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 44.9 | Not recorded | 6a30d896d33dfb23e783cc51 | | Standard | 44.8 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 44.6 | Not recorded | 6a30d896d33dfb23e783cc51 | | AdaTS | 43.3 | Not recorded | 6a30d896d33dfb23e783cc51 | ### ACP-ACC Coverage: 92.8. Result ID: 6a30f4b7fbc373592c2ca1e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 91.7. Result ID: 6a30f4b7fbc373592c2ca1ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 91.3. Result ID: 6a30f4b7fbc373592c2ca1f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"5000"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 90.7. Result ID: 6a30f4b7fbc373592c2ca1ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"5000"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 90.2. Result ID: 6a30f4b7fbc373592c2ca1e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 87. Result ID: 6a30f4b7fbc373592c2ca1f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"5000"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 86.8. Result ID: 6a30f4b7fbc373592c2ca1eb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 84.9. Result ID: 6a30f4b7fbc373592c2ca1dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 84.8. Result ID: 6a30f4b7fbc373592c2ca1e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 84. Result ID: 6a30f4b7fbc373592c2ca1e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### Retrain Coverage: 81.1. Result ID: 6a30f4b7fbc373592c2ca1db. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 77.7. Result ID: 6a30f4b7fbc373592c2ca1df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### ACP-ACC Coverage: 74.1. Result ID: 6a30f4b7fbc373592c2ca1d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### Retrain Coverage: 73.2. Result ID: 6a30f4b7fbc373592c2ca1f3. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"5000"}. This record does not assert independent reproduction. ### Retrain Coverage: 70. Result ID: 6a30f4b7fbc373592c2ca1e1. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### Retrain Coverage: 69.7. Result ID: 6a30f4b7fbc373592c2ca1ed. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 68.7. Result ID: 6a30f4b7fbc373592c2ca1de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### Retrain Coverage: 67.6. Result ID: 6a30f4b7fbc373592c2ca1e7. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### ACP-MC Coverage: 66.8. Result ID: 6a30f4b7fbc373592c2ca1d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### ACP-AEC Coverage: 56.2. Result ID: 6a30f4b7fbc373592c2ca1d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### AdaTS Coverage: 48.4. Result ID: 6a30f4b7fbc373592c2ca1da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### Standard Coverage: 46.5. Result ID: 6a30f4b7fbc373592c2ca1ee. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### Standard Coverage: 46.1. Result ID: 6a30f4b7fbc373592c2ca1f4. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"5000"}. This record does not assert independent reproduction. ### AdaTS Coverage: 45.5. Result ID: 6a30f4b7fbc373592c2ca1ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"2000"}. This record does not assert independent reproduction. ### AdaTS Coverage: 45.4. Result ID: 6a30f4b7fbc373592c2ca1e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### Standard Coverage: 45.1. Result ID: 6a30f4b7fbc373592c2ca1dc. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"200"}. This record does not assert independent reproduction. ### Standard Coverage: 44.9. Result ID: 6a30f4b7fbc373592c2ca1e2. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"500"}. This record does not assert independent reproduction. ### Standard Coverage: 44.8. Result ID: 6a30f4b7fbc373592c2ca1e8. [Reporting paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. ### AdaTS Coverage: 44.6. Result ID: 6a30f4b7fbc373592c2ca1f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"5000"}. This record does not assert independent reproduction. ### AdaTS Coverage: 43.3. Result ID: 6a30f4b7fbc373592c2ca1e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of Calibration Samples":"1000"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.