Using CORE-Bench as a case study, the paper shows that saturated benchmarks can still deliver insights on efficiency, reliability, model-scaffold differences, and human collaboration even after accuracy plateaus, and introduces improved benchmark versions plus a small randomized experiment demonstra
Journal of Business and Economic Statistics , volume =
3 Pith papers cite this work, alongside 355 external citations. Polarity classification is still indexing.
3
Pith papers citing it
355
external citations · external index
years
2026 3representative citing papers
Tabular foundation models, used zero-shot, match or beat tuned gradient boosting on average in credit PD and LGD benchmarks, with a larger edge on small datasets.
Simulations recommend the Mancl-DeRouen correction with t-distribution for continuous outcomes and the Morel-Bokossa-Neerchal estimator for binary outcomes in ETI models for SW-CRTs, while long-term effect estimates remain unstable.
citing papers explorer
-
Life After Benchmark Saturation: A Case Study of CORE-Bench
Using CORE-Bench as a case study, the paper shows that saturated benchmarks can still deliver insights on efficiency, reliability, model-scaffold differences, and human collaboration even after accuracy plateaus, and introduces improved benchmark versions plus a small randomized experiment demonstra
-
Foundation Models for Credit Risk Prediction: A Game Changer?
Tabular foundation models, used zero-shot, match or beat tuned gradient boosting on average in credit PD and LGD benchmarks, with a larger edge on small datasets.
-
Which Small-Sample Correction Should Be Used When Analyzing Stepped-Wedge Designs with Time-Varying Treatment Effects?
Simulations recommend the Mancl-DeRouen correction with t-distribution for continuous outcomes and the Morel-Bokossa-Neerchal estimator for binary outcomes in ETI models for SW-CRTs, while long-term effect estimates remain unstable.