The full narrative is unavailable.
The original evidence text could not be loaded. Use the source record below; availability of linked files is checked separately.
Open the original HTML fileAll findingsPublished research
Voidly ResearchPublished
Tabular MAE self-supervised pretrain lost to v3.3 (stratified F1 0.573 vs 0.729, LOCO 0.645 vs 0.870) — kept v3.3
We tested SSL pretraining (tabular masked-autoencoder, He/Bahri-style) on a 9,722 country-day unlabeled superset, then fine-tuned on the same 4,237 labeled rows v3.3 uses. Stratified 5-fold F1 0.573 (v3.3 baseline 0.729) and LOCO median F1 0.645 (v3.3 baseline 0.870). Both promote floors failed by…
Read the full published summary
We tested SSL pretraining (tabular masked-autoencoder, He/Bahri-style) on a 9,722 country-day unlabeled superset, then fine-tuned on the same 4,237 labeled rows v3.3 uses. Stratified 5-fold F1 0.573 (v3.3 baseline 0.729) and LOCO median F1 0.645 (v3.3 baseline 0.870). Both promote floors failed by wide margins. v3.3 stays in production unchanged. Second SSL-style negative result after TabPFN — pattern documented.
The source record.
Original source links and labels. Linked responses may have changed since publication.