# Annotator Modeling on AG News Source: [Annotator Modeling on AG News]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:58:49.091Z Evaluation of Annotator Modeling performance on the AG News dataset, typically measured using AUROC. 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 | Annotator Modeling | | Dataset (including any stated split) | agnews | | Metric | AUROC | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [AUROC](): Higher is better; unit: PERCENT. ## Recorded results | Method | AUROC | Result date | Report paper | | --- | --- | --- | --- | | union-net | 93.1 | Not recorded | 68fa73141e209131cea5a5f9 | | crowd-layer | 93 | Not recorded | 68fa73141e209131cea5a5f9 | | union-net | 93 | Not recorded | 68fa73141e209131cea5a5f9 | | crowd-layer | 93 | Not recorded | 68fa73141e209131cea5a5f9 | | annot-mix | 92.7 | Not recorded | 68fa73141e209131cea5a5f9 | | annot-mix | 92.7 | Not recorded | 68fa73141e209131cea5a5f9 | | trace-reg | 92.4 | Not recorded | 68fa73141e209131cea5a5f9 | | geo-reg-f | 92.4 | Not recorded | 68fa73141e209131cea5a5f9 | | geo-reg-f | 92.2 | Not recorded | 68fa73141e209131cea5a5f9 | | trace-reg | 92.1 | Not recorded | 68fa73141e209131cea5a5f9 | | geo-reg-w | 89.7 | Not recorded | 68fa73141e209131cea5a5f9 | | geo-reg-w | 89.4 | Not recorded | 68fa73141e209131cea5a5f9 | | madl | 89.2 | Not recorded | 68fa73141e209131cea5a5f9 | | madl | 88.1 | Not recorded | 68fa73141e209131cea5a5f9 | | crowd-ar | 63.4 | Not recorded | 68fa73141e209131cea5a5f9 | | crowd-ar | 63.1 | Not recorded | 68fa73141e209131cea5a5f9 | | conal | 61.7 | Not recorded | 68fa73141e209131cea5a5f9 | | conal | 61.3 | Not recorded | 68fa73141e209131cea5a5f9 | ### union-net AUROC: 93.1. Result ID: 6a213e27fbc373592c1cf4ab. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### crowd-layer AUROC: 93. Result ID: 6a213e27fbc373592c1cf49f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### union-net AUROC: 93. Result ID: 6a213e27fbc373592c1cf4a2. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### crowd-layer AUROC: 93. Result ID: 6a213e27fbc373592c1cf4a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### annot-mix AUROC: 92.7. Result ID: 6a213e27fbc373592c1cf4a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### annot-mix AUROC: 92.7. Result ID: 6a213e27fbc373592c1cf4b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### trace-reg AUROC: 92.4. Result ID: 6a213e27fbc373592c1cf4a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### geo-reg-f AUROC: 92.4. Result ID: 6a213e27fbc373592c1cf4ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### geo-reg-f AUROC: 92.2. Result ID: 6a213e27fbc373592c1cf4a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### trace-reg AUROC: 92.1. Result ID: 6a213e27fbc373592c1cf4a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### geo-reg-w AUROC: 89.7. Result ID: 6a213e27fbc373592c1cf4ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### geo-reg-w AUROC: 89.4. Result ID: 6a213e27fbc373592c1cf4a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### madl AUROC: 89.2. Result ID: 6a213e27fbc373592c1cf4ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### madl AUROC: 88.1. Result ID: 6a213e27fbc373592c1cf4a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### crowd-ar AUROC: 63.4. Result ID: 6a213e27fbc373592c1cf4a6. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### crowd-ar AUROC: 63.1. Result ID: 6a213e27fbc373592c1cf4af. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### conal AUROC: 61.7. Result ID: 6a213e27fbc373592c1cf4a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Last Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. ### conal AUROC: 61.3. Result ID: 6a213e27fbc373592c1cf4aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Epoch":"Best Epoch","False label fraction":"56.8"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.