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.
All findingsPublished research
Voidly ResearchPublished
Classifier v3.4: regime-cluster fine-tuning didn't fix the tail. Held.
Tried per-regime-cluster fine-tuning heads (MENA, post-Soviet, East Asia, SE Asia, LATAM, Sub-Sahara) stacked on top of v3.3 to recover the 16 countries that regressed under v3.3. The stacking head learns to mostly ignore the cluster heads (base coef 9.8 vs cluster coefs in [-0.83, +0.64]). LOCO…
Read the full published summary
Tried per-regime-cluster fine-tuning heads (MENA, post-Soviet, East Asia, SE Asia, LATAM, Sub-Sahara) stacked on top of v3.3 to recover the 16 countries that regressed under v3.3. The stacking head learns to mostly ignore the cluster heads (base coef 9.8 vs cluster coefs in [-0.83, +0.64]). LOCO median F1 drops 0.870 to 0.833, only 1 of 16 regression countries improves by ≥3pp (UZ +7pp), and 2 countries regress further (GE -9pp, SY -5pp). Both promotion gates fail. v3.3 stays in production. Documented as a real negative result.
The source record.
Original source links and labels. Linked responses may have changed since publication.