# Watermark Detectability on C4 RealNewsLike Dipper-2 (test) Source: [Watermark Detectability on C4 RealNewsLike Dipper-2 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:25:07.567Z Evaluation of watermark detectability performance using AUC and True Positive Rate (TPR) on the specific test split of the C4 RealNewsLike dataset subjected to the Dipper-2 perturbation. 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 | Watermark Detectability | | Dataset (including any stated split) | C4 RealNewsLike Dipper-2 (test) | | Metric | AUC | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [AUC](): Higher is better; unit: PERCENT. - [TPR](): Higher is better; unit: PERCENT. ## Recorded results | Method | AUC | Result date | Report paper | | --- | --- | --- | --- | | MarkTune | 85.9 | Not recorded | 693115d9d6b0dd3342933da6 | | MarkTune | 85.1 | Not recorded | 693115d9d6b0dd3342933da6 | | GaussMark | 79.5 | Not recorded | 693115d9d6b0dd3342933da6 | | Gumbel-max | 72.1 | Not recorded | 693115d9d6b0dd3342933da6 | | Gumbel-max | 71.1 | Not recorded | 693115d9d6b0dd3342933da6 | | SynthID | 71 | Not recorded | 693115d9d6b0dd3342933da6 | | SynthID | 70 | Not recorded | 693115d9d6b0dd3342933da6 | | GaussMark | 68.7 | Not recorded | 693115d9d6b0dd3342933da6 | | KGW-2 | 61.6 | Not recorded | 693115d9d6b0dd3342933da6 | | KGW-2 | 61.4 | Not recorded | 693115d9d6b0dd3342933da6 | | KGW-D | 59 | Not recorded | 693115d9d6b0dd3342933da6 | | KGW-D | 58.9 | Not recorded | 693115d9d6b0dd3342933da6 | | KGW-1 | 57.3 | Not recorded | 693115d9d6b0dd3342933da6 | | KGW-1 | 55.1 | Not recorded | 693115d9d6b0dd3342933da6 | ### MarkTune AUC: 85.9. Result ID: 69998b265698665ec4fd0d58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama2-7B","Temperature":"1.0"}. This record does not assert independent reproduction. ### MarkTune AUC: 85.1. Result ID: 69998b265698665ec4fd0d51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Temperature":"0.7"}. This record does not assert independent reproduction. ### GaussMark AUC: 79.5. Result ID: 69998b265698665ec4fd0d50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Temperature":"0.7"}. This record does not assert independent reproduction. ### Gumbel-max AUC: 72.1. Result ID: 69998b265698665ec4fd0d4d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Temperature":"0.7"}. This record does not assert independent reproduction. ### Gumbel-max AUC: 71.1. Result ID: 69998b265698665ec4fd0d54. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama2-7B","Temperature":"1.0"}. This record does not assert independent reproduction. ### SynthID AUC: 71. Result ID: 69998b265698665ec4fd0d55. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama2-7B","Temperature":"1.0"}. This record does not assert independent reproduction. ### SynthID AUC: 70. Result ID: 69998b265698665ec4fd0d4e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Temperature":"0.7"}. This record does not assert independent reproduction. ### GaussMark AUC: 68.7. Result ID: 69998b265698665ec4fd0d57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama2-7B","Temperature":"1.0"}. This record does not assert independent reproduction. ### KGW-2 AUC: 61.6. Result ID: 69998b265698665ec4fd0d4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Temperature":"0.7"}. This record does not assert independent reproduction. ### KGW-2 AUC: 61.4. Result ID: 69998b265698665ec4fd0d53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama2-7B","Temperature":"1.0"}. This record does not assert independent reproduction. ### KGW-D AUC: 59. Result ID: 69998b265698665ec4fd0d56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama2-7B","Temperature":"1.0"}. This record does not assert independent reproduction. ### KGW-D AUC: 58.9. Result ID: 69998b265698665ec4fd0d4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Temperature":"0.7"}. This record does not assert independent reproduction. ### KGW-1 AUC: 57.3. Result ID: 69998b265698665ec4fd0d4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Temperature":"0.7"}. This record does not assert independent reproduction. ### KGW-1 AUC: 55.1. Result ID: 69998b265698665ec4fd0d52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama2-7B","Temperature":"1.0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.