# Machine-Generated Text Attribution on AIGTBench Source: [Machine-Generated Text Attribution on AIGTBench]() Collection index: [llms.txt]() Data updated: 2026-06-05T08:41:14.091Z Evaluation of model performance on the AIGTBench dataset for the task of Machine-Generated Text Attribution, measured using Full Macro-F1. 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 | Machine-Generated Text Attribution | | Dataset (including any stated split) | AIGTBench | | Metric | Macro F1 (Full) | | 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 - [Macro F1 (Full)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Macro F1 (Full) | Result date | Report paper | | --- | --- | --- | --- | | RidgeFT | 91.5 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 91 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.9 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.9 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.6 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.6 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.5 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.4 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.3 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.2 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 89.2 | Not recorded | 6a22589786173ad9c1468b1e | | RidgeFT | 88.9 | Not recorded | 6a22589786173ad9c1468b1e | ### RidgeFT Macro F1 (Full): 91.5. Result ID: 6a228a87fbc373592c209f2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"Llama-1"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 91. Result ID: 6a228a87fbc373592c209f2e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"Llama-1"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.9. Result ID: 6a228a87fbc373592c209f31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"Llama-3.1"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.9. Result ID: 6a228a87fbc373592c209f33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"Average"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.6. Result ID: 6a228a87fbc373592c209f2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-4o-mini"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.6. Result ID: 6a228a87fbc373592c209f34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"Average"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.5. Result ID: 6a228a87fbc373592c209f32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"Llama-3.1"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.4. Result ID: 6a228a87fbc373592c209f29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.3. Result ID: 6a228a87fbc373592c209f30. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"Llama-2"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.2. Result ID: 6a228a87fbc373592c209f2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 89.2. Result ID: 6a228a87fbc373592c209f2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"Llama-2"}. This record does not assert independent reproduction. ### RidgeFT Macro F1 (Full): 88.9. Result ID: 6a228a87fbc373592c209f2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-4o-mini"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.