# Global Source Attribution on MLAAD Closed-Set IID (test) Source: [Global Source Attribution on MLAAD Closed-Set IID (test)]() Collection index: [llms.txt]() Data updated: 2026-07-07T08:17:06.078Z Evaluation of Global Source Attribution performance on the test split of the MLAAD Closed-Set IID dataset, reporting F1-Macro score. 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 | Global Source Attribution | | Dataset (including any stated split) | MLAAD Closed-Set IID (test) | | Metric | F1-Macro (Seen IID) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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-Macro (Seen IID)](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1-Macro (Seen IID) | Result date | Report paper | | --- | --- | --- | --- | | Strategy 1 (Orthonormal Prototypes) | 95.44 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 2.A (Factorized Prototypes) | 95.36 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 1 (Orthonormal Prototypes) | 95.34 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 1 (Orthonormal Prototypes) | 95.31 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 2.A (Factorized Prototypes) | 95.21 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 1 (Orthonormal Prototypes) | 95.2 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 2.A (Factorized Prototypes) | 95.17 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Baseline (ArcFace) | 95.11 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 2.B (Residual Modeling) | 95.09 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 2.B (Residual Modeling) | 94.99 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 2.A (Factorized Prototypes) | 94.93 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 2.B (Residual Modeling) | 94.62 | Not recorded | 6a4c87e385dba69fef8b23d0 | | Strategy 2.B (Residual Modeling) | 94.51 | Not recorded | 6a4c87e385dba69fef8b23d0 | ### Strategy 1 (Orthonormal Prototypes) F1-Macro (Seen IID): 95.44. Result ID: 6a4cb5e760b88bb339c85409. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"1.0"}. This record does not assert independent reproduction. ### Strategy 2.A (Factorized Prototypes) F1-Macro (Seen IID): 95.36. Result ID: 6a4cb5e760b88bb339c8540d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"1.0"}. This record does not assert independent reproduction. ### Strategy 1 (Orthonormal Prototypes) F1-Macro (Seen IID): 95.34. Result ID: 6a4cb5e760b88bb339c85407. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.05"}. This record does not assert independent reproduction. ### Strategy 1 (Orthonormal Prototypes) F1-Macro (Seen IID): 95.31. Result ID: 6a4cb5e760b88bb339c85408. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.1"}. This record does not assert independent reproduction. ### Strategy 2.A (Factorized Prototypes) F1-Macro (Seen IID): 95.21. Result ID: 6a4cb5e760b88bb339c8540c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.1"}. This record does not assert independent reproduction. ### Strategy 1 (Orthonormal Prototypes) F1-Macro (Seen IID): 95.2. Result ID: 6a4cb5e760b88bb339c85406. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.0"}. This record does not assert independent reproduction. ### Strategy 2.A (Factorized Prototypes) F1-Macro (Seen IID): 95.17. Result ID: 6a4cb5e760b88bb339c8540b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.05"}. This record does not assert independent reproduction. ### Baseline (ArcFace) F1-Macro (Seen IID): 95.11. Result ID: 6a4cb5e760b88bb339c85405. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"MSE (λ)":"–"}. This record does not assert independent reproduction. ### Strategy 2.B (Residual Modeling) F1-Macro (Seen IID): 95.09. Result ID: 6a4cb5e760b88bb339c85411. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"1.0"}. This record does not assert independent reproduction. ### Strategy 2.B (Residual Modeling) F1-Macro (Seen IID): 94.99. Result ID: 6a4cb5e760b88bb339c85410. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.1"}. This record does not assert independent reproduction. ### Strategy 2.A (Factorized Prototypes) F1-Macro (Seen IID): 94.93. Result ID: 6a4cb5e760b88bb339c8540a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.0"}. This record does not assert independent reproduction. ### Strategy 2.B (Residual Modeling) F1-Macro (Seen IID): 94.62. Result ID: 6a4cb5e760b88bb339c8540f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.05"}. This record does not assert independent reproduction. ### Strategy 2.B (Residual Modeling) F1-Macro (Seen IID): 94.51. Result ID: 6a4cb5e760b88bb339c8540e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MSE (λ)":"0.0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.