# Tabular Learning on Corrupted Extra Features Suite (AL, CH, CO, EY, GE, HE, HI, HO, JA, MI, OT, YE) (test) Source: [Tabular Learning on Corrupted Extra Features Suite (AL, CH, CO, EY, GE, HE, HI, HO, JA, MI, OT, YE) (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:04.658Z Evaluation of Tabular Learning performance across the 12 specified corrupted feature sets (AL, CH, CO, EY, GE, HE, HI, HO, JA, MI, OT, YE) on the test split of the Corrupted Extra Features Suite. 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 | Tabular Learning | | Dataset (including any stated split) | Corrupted Extra Features Suite (AL, CH, CO, EY, GE, HE, HI, HO, JA, MI, OT, YE) (test) | | Metric | Score (AL) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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 - [Score (AL)](): Higher is better; unit: SCALAR. - [Score (CH)](): Higher is better; unit: SCALAR. - [Score (CO)](): Higher is better; unit: SCALAR. - [Score (EY)](): Higher is better; unit: SCALAR. - [Score (GE)](): Higher is better; unit: SCALAR. - [Score (HE)](): Higher is better; unit: SCALAR. - [Score (HI)](): Higher is better; unit: SCALAR. - [Score (HO)](): Higher is better; unit: SCALAR. - [Score (JA)](): Higher is better; unit: SCALAR. - [Score (MI)](): Higher is better; unit: SCALAR. - [Score (OT)](): Higher is better; unit: SCALAR. - [Score (YE)](): Higher is better; unit: SCALAR. - [Rank](): Lower is better; unit: SCALAR. ## Recorded results | Method | Score (AL) | Result date | Report paper | | --- | --- | --- | --- | | Deep Lasso + FT | 0.963 | Not recorded | 68fa71211e209131cea4f5bd | | Deep Lasso | 0.962 | Not recorded | 68fa71211e209131cea4f5bd | | No FS + FT | 0.962 | Not recorded | 68fa71211e209131cea4f5bd | | Deep Lasso + FT | 0.961 | Not recorded | 68fa71211e209131cea4f5bd | | Deep Lasso + MLP | 0.961 | Not recorded | 68fa71211e209131cea4f5bd | | No FS + FT | 0.96 | Not recorded | 68fa71211e209131cea4f5bd | | No FS + MLP | 0.96 | Not recorded | 68fa71211e209131cea4f5bd | | Deep Lasso + MLP | 0.959 | Not recorded | 68fa71211e209131cea4f5bd | | Deep Lasso | 0.959 | Not recorded | 68fa71211e209131cea4f5bd | | No FS | 0.959 | Not recorded | 68fa71211e209131cea4f5bd | | Deep Lasso + MLP | 0.959 | Not recorded | 68fa71211e209131cea4f5bd | | Deep Lasso | 0.957 | Not recorded | 68fa71211e209131cea4f5bd | | Deep Lasso + MLP | 0.955 | Not recorded | 68fa71211e209131cea4f5bd | | No FS + MLP | 0.952 | Not recorded | 68fa71211e209131cea4f5bd | | No FS + MLP | 0.946 | Not recorded | 68fa71211e209131cea4f5bd | | No FS | 0.941 | Not recorded | 68fa71211e209131cea4f5bd | | No FS | 0.925 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.923 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.923 | Not recorded | 68fa71211e209131cea4f5bd | | No FS + MLP | 0.921 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.917 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.858 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.858 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.854 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.854 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.839 | Not recorded | 68fa71211e209131cea4f5bd | | XGBoost Baseline | 0.83 | Not recorded | 68fa71211e209131cea4f5bd | ### Deep Lasso + FT Score (AL): 0.963. Result ID: 69919c4e3a6c3148490953ff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Feature Selection %":"50"}. This record does not assert independent reproduction. ### Deep Lasso Score (AL): 0.962. Result ID: 69919c4e3a6c3148490953f6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"% extra features":"50","Backbone":"FT"}. This record does not assert independent reproduction. ### No FS + FT Score (AL): 0.962. Result ID: 69919c4e3a6c3148490953fe. [Reporting paper]() Recorded evaluation configuration: {"Feature Selection %":"50"}. This record does not assert independent reproduction. ### Deep Lasso + FT Score (AL): 0.961. Result ID: 69919c4e3a6c31484909531c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"extra\_features\_percentage":"50%","backbone":"FT-Transformer"}. This record does not assert independent reproduction. ### Deep Lasso + MLP Score (AL): 0.961. Result ID: 69919c4e3a6c3148490953f9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Feature Selection %":"50"}. This record does not assert independent reproduction. ### No FS + FT Score (AL): 0.96. Result ID: 69919c4e3a6c31484909531b. [Reporting paper]() Recorded evaluation configuration: {"extra\_features\_percentage":"50%","backbone":"FT-Transformer"}. This record does not assert independent reproduction. ### No FS + MLP Score (AL): 0.96. Result ID: 69919c4e3a6c3148490953f8. [Reporting paper]() Recorded evaluation configuration: {"Feature Selection %":"50"}. This record does not assert independent reproduction. ### Deep Lasso + MLP Score (AL): 0.959. Result ID: 69919c4e3a6c314849095319. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"extra\_features\_percentage":"75%","backbone":"MLP"}. This record does not assert independent reproduction. ### Deep Lasso Score (AL): 0.959. Result ID: 69919c4e3a6c3148490953f0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"% extra features":"50","Backbone":"MLP"}. This record does not assert independent reproduction. ### No FS Score (AL): 0.959. Result ID: 69919c4e3a6c3148490953f5. [Reporting paper]() Recorded evaluation configuration: {"% extra features":"50","Backbone":"FT"}. This record does not assert independent reproduction. ### Deep Lasso + MLP Score (AL): 0.959. Result ID: 69919c4e3a6c3148490953fc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Feature Selection %":"75"}. This record does not assert independent reproduction. ### Deep Lasso Score (AL): 0.957. Result ID: 69919c4e3a6c3148490953f3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"% extra features":"75","Backbone":"MLP"}. This record does not assert independent reproduction. ### Deep Lasso + MLP Score (AL): 0.955. Result ID: 69919c4e3a6c314849095316. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"extra\_features\_percentage":"50%","backbone":"MLP"}. This record does not assert independent reproduction. ### No FS + MLP Score (AL): 0.952. Result ID: 69919c4e3a6c3148490953fb. [Reporting paper]() Recorded evaluation configuration: {"Feature Selection %":"75"}. This record does not assert independent reproduction. ### No FS + MLP Score (AL): 0.946. Result ID: 69919c4e3a6c314849095315. [Reporting paper]() Recorded evaluation configuration: {"extra\_features\_percentage":"50%","backbone":"MLP"}. This record does not assert independent reproduction. ### No FS Score (AL): 0.941. Result ID: 69919c4e3a6c3148490953ef. [Reporting paper]() Recorded evaluation configuration: {"% extra features":"50","Backbone":"MLP"}. This record does not assert independent reproduction. ### No FS Score (AL): 0.925. Result ID: 69919c4e3a6c3148490953f2. [Reporting paper]() Recorded evaluation configuration: {"% extra features":"75","Backbone":"MLP"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.923. Result ID: 69919c4e3a6c3148490953f7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Feature Selection %":"50"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.923. Result ID: 69919c4e3a6c3148490953fd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Feature Selection %":"50","comparison\_group":"fine-tuning models"}. This record does not assert independent reproduction. ### No FS + MLP Score (AL): 0.921. Result ID: 69919c4e3a6c314849095318. [Reporting paper]() Recorded evaluation configuration: {"extra\_features\_percentage":"75%","backbone":"MLP"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.917. Result ID: 69919c4e3a6c3148490953fa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Feature Selection %":"75"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.858. Result ID: 69919c4e3a6c3148490953ee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"% extra features":"50"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.858. Result ID: 69919c4e3a6c3148490953f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"% extra features":"50","Comparison Context":"Against FT Backbone"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.854. Result ID: 69919c4e3a6c314849095314. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"extra\_features\_percentage":"50%","backbone":"XGBoost"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.854. Result ID: 69919c4e3a6c31484909531a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"extra\_features\_percentage":"50%","backbone":"XGBoost","comparison\_group":"FT-Transformer"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.839. Result ID: 69919c4e3a6c3148490953f1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"% extra features":"75"}. This record does not assert independent reproduction. ### XGBoost Baseline Score (AL): 0.83. Result ID: 69919c4e3a6c314849095317. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"extra\_features\_percentage":"75%","backbone":"XGBoost"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.