# Time-Series Anomaly Detection on PSM (F1, AUROC, AUPR, VUS-ROC, VUS-PR) Source: [Time-Series Anomaly Detection on PSM (F1, AUROC, AUPR, VUS-ROC, VUS-PR)]() Collection index: [llms.txt]() Data updated: 2026-04-16T08:24:47.848Z Evaluation of Time-Series Anomaly Detection performance on the PSM dataset, reporting F1 score, AUROC, AUPR, VUS-ROC, and VUS-PR. 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 | Time-Series Anomaly Detection | | Dataset (including any stated split) | PSM | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [AUROC](): Higher is better; unit: PERCENT. - [AUPR](): Higher is better; unit: PERCENT. - [VUS-ROC](): Higher is better; unit: PERCENT. - [VUS-PR](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | ASTER | 51.2 | Not recorded | 69e06d2d7d0172140ec7cbcb | | TranAD | 40.3 | Not recorded | 69e06d2d7d0172140ec7cbcb | | LLMMixer | 18.6 | Not recorded | 69e06d2d7d0172140ec7cbcb | | Timer | 14.3 | Not recorded | 69e06d2d7d0172140ec7cbcb | | Chronos | 13.1 | Not recorded | 69e06d2d7d0172140ec7cbcb | | Moment | 11.7 | Not recorded | 69e06d2d7d0172140ec7cbcb | | CALF | 10.2 | Not recorded | 69e06d2d7d0172140ec7cbcb | | UniTime | 9.7 | Not recorded | 69e06d2d7d0172140ec7cbcb | | GPT4TS | 8.9 | Not recorded | 69e06d2d7d0172140ec7cbcb | | TimesNet | 8.8 | Not recorded | 69e06d2d7d0172140ec7cbcb | | TimesFM | 8.2 | Not recorded | 69e06d2d7d0172140ec7cbcb | | DAGMM | 0.7 | Not recorded | 69e06d2d7d0172140ec7cbcb | ### ASTER F1 Score: 51.2. Result ID: 69e09cce47f34ce924c9d2f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"LLM-based"}. This record does not assert independent reproduction. ### TranAD F1 Score: 40.3. Result ID: 69e09cce47f34ce924c9d2ee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Deep Learning-based"}. This record does not assert independent reproduction. ### LLMMixer F1 Score: 18.6. Result ID: 69e09cce47f34ce924c9d2f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"LLM-based"}. This record does not assert independent reproduction. ### Timer F1 Score: 14.3. Result ID: 69e09cce47f34ce924c9d2ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Pre-Trained Models"}. This record does not assert independent reproduction. ### Chronos F1 Score: 13.1. Result ID: 69e09cce47f34ce924c9d2f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Pre-Trained Models"}. This record does not assert independent reproduction. ### Moment F1 Score: 11.7. Result ID: 69e09cce47f34ce924c9d2f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Pre-Trained Models"}. This record does not assert independent reproduction. ### CALF F1 Score: 10.2. Result ID: 69e09cce47f34ce924c9d2f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"LLM-based"}. This record does not assert independent reproduction. ### UniTime F1 Score: 9.7. Result ID: 69e09cce47f34ce924c9d2f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"LLM-based"}. This record does not assert independent reproduction. ### GPT4TS F1 Score: 8.9. Result ID: 69e09cce47f34ce924c9d2f3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"LLM-based"}. This record does not assert independent reproduction. ### TimesNet F1 Score: 8.8. Result ID: 69e09cce47f34ce924c9d2ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Deep Learning-based"}. This record does not assert independent reproduction. ### TimesFM F1 Score: 8.2. Result ID: 69e09cce47f34ce924c9d2f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Pre-Trained Models"}. This record does not assert independent reproduction. ### DAGMM F1 Score: 0.7. Result ID: 69e09cce47f34ce924c9d2ec. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Deep Learning-based"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.