# Failure Detection on LIZ-IG Source: [Failure Detection on LIZ-IG]() Collection index: [llms.txt]() Data updated: 2026-04-01T08:55:34.058Z Evaluation of model performance on the LIZ-IG dataset for the Failure Detection task, measured using E-AURC. 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 | Failure Detection | | Dataset (including any stated split) | LIZ-IG | | Metric | E-AURC | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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 - [E-AURC](): Higher is better; unit: SCALAR. ## Recorded results | Method | E-AURC | Result date | Report paper | | --- | --- | --- | --- | | ICA | 0.33 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | ICA | 0.33 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | AQA | 0.33 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | AVG | 0.33 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | AQA | 0.33 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | AQA | 0.32 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | AVG | 0.32 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | AQA | 0.32 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | AQA | 0.32 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | AQA | 0.31 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | BCA | 0.3 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | PLM | 0.29 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | PLM | 0.28 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | PLM | 0.28 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | QFR | 0.28 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | PLM | 0.28 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | ATA | 0.27 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | PLM | 0.27 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | PLM | 0.27 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | QFR | 0.26 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | BCA | 0.26 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | ATA | 0.24 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | ATA | 0.23 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | ATA | 0.21 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | ATA | 0.21 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | GMM-All | 0.19 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | GMM-Spa | 0.18 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | GMM-Int | 0.17 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | GMM-Spa | 0.17 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | ATA | 0.17 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | GMM-All | 0.16 | Not recorded | 69cca6a90636e5bf4afcbcc5 | | GMM-Int | 0.16 | Not recorded | 69cca6a90636e5bf4afcbcc5 | ### ICA E-AURC: 0.33. Result ID: 69ccdd7347f34ce924b6afc5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD"}. This record does not assert independent reproduction. ### ICA E-AURC: 0.33. Result ID: 69ccdd7347f34ce924b6b0c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### AQA E-AURC: 0.33. Result ID: 69ccdd7347f34ce924b6b0c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"0.6","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### AVG E-AURC: 0.33. Result ID: 69ccdd7347f34ce924b6b0c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### AQA E-AURC: 0.33. Result ID: 69ccdd7347f34ce924b6b0c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"0.75","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### AQA E-AURC: 0.32. Result ID: 69ccdd7347f34ce924b6afc6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":".75"}. This record does not assert independent reproduction. ### AVG E-AURC: 0.32. Result ID: 69ccdd7347f34ce924b6afc7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD"}. This record does not assert independent reproduction. ### AQA E-AURC: 0.32. Result ID: 69ccdd7347f34ce924b6afc8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":".6"}. This record does not assert independent reproduction. ### AQA E-AURC: 0.32. Result ID: 69ccdd7347f34ce924b6b0c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"0.9","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### AQA E-AURC: 0.31. Result ID: 69ccdd7347f34ce924b6afc4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":".9"}. This record does not assert independent reproduction. ### BCA E-AURC: 0.3. Result ID: 69ccdd7347f34ce924b6afbd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD"}. This record does not assert independent reproduction. ### PLM E-AURC: 0.29. Result ID: 69ccdd7347f34ce924b6b0c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter":"50","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### PLM E-AURC: 0.28. Result ID: 69ccdd7347f34ce924b6afc1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":"20"}. This record does not assert independent reproduction. ### PLM E-AURC: 0.28. Result ID: 69ccdd7347f34ce924b6afc3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":"50"}. This record does not assert independent reproduction. ### QFR E-AURC: 0.28. Result ID: 69ccdd7347f34ce924b6b0ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### PLM E-AURC: 0.28. Result ID: 69ccdd7347f34ce924b6b0c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter":"20","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### ATA E-AURC: 0.27. Result ID: 69ccdd7347f34ce924b6afbe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":".3"}. This record does not assert independent reproduction. ### PLM E-AURC: 0.27. Result ID: 69ccdd7347f34ce924b6afc0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":"10"}. This record does not assert independent reproduction. ### PLM E-AURC: 0.27. Result ID: 69ccdd7347f34ce924b6b0c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameter":"10","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### QFR E-AURC: 0.26. Result ID: 69ccdd7347f34ce924b6afb9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD"}. This record does not assert independent reproduction. ### BCA E-AURC: 0.26. Result ID: 69ccdd7347f34ce924b6b0bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### ATA E-AURC: 0.24. Result ID: 69ccdd7347f34ce924b6b0bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"0.3","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### ATA E-AURC: 0.23. Result ID: 69ccdd7347f34ce924b6afbf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":".5"}. This record does not assert independent reproduction. ### ATA E-AURC: 0.21. Result ID: 69ccdd7347f34ce924b6afc2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD","Aggregation parameter":".7"}. This record does not assert independent reproduction. ### ATA E-AURC: 0.21. Result ID: 69ccdd7347f34ce924b6b0be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"0.5","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### GMM-All E-AURC: 0.19. Result ID: 69ccdd7347f34ce924b6b0b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### GMM-Spa E-AURC: 0.18. Result ID: 69ccdd7347f34ce924b6afbc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD"}. This record does not assert independent reproduction. ### GMM-Int E-AURC: 0.17. Result ID: 69ccdd7347f34ce924b6afbb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD"}. This record does not assert independent reproduction. ### GMM-Spa E-AURC: 0.17. Result ID: 69ccdd7347f34ce924b6b0bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### ATA E-AURC: 0.17. Result ID: 69ccdd7347f34ce924b6b0c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Threshold":"0.7","Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. ### GMM-All E-AURC: 0.16. Result ID: 69ccdd7347f34ce924b6afba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Method":"MCD"}. This record does not assert independent reproduction. ### GMM-Int E-AURC: 0.16. Result ID: 69ccdd7347f34ce924b6b0bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Uncertainty Framework":"Maximum Softmax Probability (MSP)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.