# Classification on Adult (test) (macro F1-score) Source: [Classification on Adult (test) (macro F1-score)]() Collection index: [llms.txt]() Data updated: 2026-03-23T11:57:15.770Z Evaluation of Classification performance on the test split of the Adult dataset, measured by macro F1-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 | Classification | | Dataset (including any stated split) | Adult (AD) (test) | | Metric | Macro F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 36 of 36 | | 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 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Macro F1 Score | Result date | Report paper | | --- | --- | --- | --- | | Var-T-JEPA | 92.3 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 92 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 91.8 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 91.7 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 91.6 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 91.5 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 88.8 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 88.1 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 88 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 87.9 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 87.8 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 87.7 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 87 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 86.4 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 86.3 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 86.2 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 86.1 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | XGBoost | 86 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 85.9 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | T-JEPA | 85 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 85 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 84.9 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | T-JEPA | 84.9 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 84.8 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 84.8 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | T-JEPA | 84.7 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 84.7 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | T-JEPA | 84.6 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | MLP | 84.5 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | Var-T-JEPA | 84.5 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | T-JEPA | 84.5 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | ResNet | 84.4 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | T-JEPA | 84.2 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | AutoInt | 68.7 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | FT-Trans | 68.7 | Not recorded | 69c0c9160636e5bf4afc3cd0 | | DCNv2 | 68.4 | Not recorded | 69c0c9160636e5bf4afc3cd0 | ### Var-T-JEPA Macro F1 Score: 92.3. Result ID: 69c12a9047f34ce924a9d56a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XGBoost","Evaluation Coverage":"50%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 92. Result ID: 69c12a9047f34ce924a9d558. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Evaluation Coverage":"50%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 91.8. Result ID: 69c12a9047f34ce924a9d55e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"AutoInt","Evaluation Coverage":"50%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 91.7. Result ID: 69c12a9047f34ce924a9d564. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"FT-Trans","Evaluation Coverage":"50%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 91.6. Result ID: 69c12a9047f34ce924a9d552. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DCNv2","Evaluation Coverage":"50%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 91.5. Result ID: 69c12a9047f34ce924a9d54c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP","Evaluation Coverage":"50%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 88.8. Result ID: 69c12a9047f34ce924a9d569. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XGBoost","Evaluation Coverage":"20%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 88.1. Result ID: 69c12a9047f34ce924a9d557. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Evaluation Coverage":"20%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 88. Result ID: 69c12a9047f34ce924a9d55d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"AutoInt","Evaluation Coverage":"20%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 87.9. Result ID: 69c12a9047f34ce924a9d563. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"FT-Trans","Evaluation Coverage":"20%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 87.8. Result ID: 69c12a9047f34ce924a9d551. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DCNv2","Evaluation Coverage":"20%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 87.7. Result ID: 69c12a9047f34ce924a9d54b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP","Evaluation Coverage":"20%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 87. Result ID: 69c12a9047f34ce924a9d568. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XGBoost","Evaluation Coverage":"10%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 86.4. Result ID: 69c12a9047f34ce924a9d556. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Evaluation Coverage":"10%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 86.3. Result ID: 69c12a9047f34ce924a9d55c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"AutoInt","Evaluation Coverage":"10%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 86.2. Result ID: 69c12a9047f34ce924a9d562. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"FT-Trans","Evaluation Coverage":"10%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 86.1. Result ID: 69c12a9047f34ce924a9d550. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DCNv2","Evaluation Coverage":"10%"}. This record does not assert independent reproduction. ### XGBoost Macro F1 Score: 86. Result ID: 69c12a9047f34ce924a9d565. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"XGBoost","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 85.9. Result ID: 69c12a9047f34ce924a9d54a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP","Evaluation Coverage":"10%"}. This record does not assert independent reproduction. ### T-JEPA Macro F1 Score: 85. Result ID: 69c12a9047f34ce924a9d566. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XGBoost","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 85. Result ID: 69c12a9047f34ce924a9d567. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XGBoost","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 84.9. Result ID: 69c12a9047f34ce924a9d555. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### T-JEPA Macro F1 Score: 84.9. Result ID: 69c12a9047f34ce924a9d55a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"AutoInt","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 84.8. Result ID: 69c12a9047f34ce924a9d54f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DCNv2","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 84.8. Result ID: 69c12a9047f34ce924a9d55b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"AutoInt","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### T-JEPA Macro F1 Score: 84.7. Result ID: 69c12a9047f34ce924a9d560. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"FT-Trans","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 84.7. Result ID: 69c12a9047f34ce924a9d561. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"FT-Trans","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### T-JEPA Macro F1 Score: 84.6. Result ID: 69c12a9047f34ce924a9d54e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DCNv2","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### MLP Macro F1 Score: 84.5. Result ID: 69c12a9047f34ce924a9d547. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"MLP","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### Var-T-JEPA Macro F1 Score: 84.5. Result ID: 69c12a9047f34ce924a9d549. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### T-JEPA Macro F1 Score: 84.5. Result ID: 69c12a9047f34ce924a9d554. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### ResNet Macro F1 Score: 84.4. Result ID: 69c12a9047f34ce924a9d553. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### T-JEPA Macro F1 Score: 84.2. Result ID: 69c12a9047f34ce924a9d548. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MLP","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### AutoInt Macro F1 Score: 68.7. Result ID: 69c12a9047f34ce924a9d559. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"AutoInt","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### FT-Trans Macro F1 Score: 68.7. Result ID: 69c12a9047f34ce924a9d55f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"FT-Trans","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. ### DCNv2 Macro F1 Score: 68.4. Result ID: 69c12a9047f34ce924a9d54d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DCNv2","Evaluation Coverage":"100%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.