Unverified50% confidenceDecision RuleExact time
Cross-encoders are only suitable for re-ranking candidate sets (typically 20–100 items), not for full-corpus retrieval.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 29-million-parameter encoder trained by the researchers achieved a popularity-weighted cross-fold AUC of only 0.486 on 985 statements, indistinguishable from the corpus prior.67% similarUnverifiedIn few-shot scenarios (e.g., approximately 20 samples per class), multi-class subdivision should be abandoned, all defects should be collapsed into a binary classification problem (defective/non-defective), and specific classification should be left to manual post-processing.66% similarUnverifiedA hand-crafted library of 22 calculators achieved perfect accuracy on the 440 cases it supported, but abstained on the remaining cases, yielding an overall coverage rate of only 40.0%.63% similarUnverifiedIn a scenario with 1,700 easy cases and 100 difficult multilingual cases, even if half of the difficult cases fail entirely, the aggregate pass rate may only drop from 97% to around 93%61% similarUnverifiedVendor-reported coding scores are typically measured on carefully curated subsets, and results reproduced by independent organizations on the full test set are often lower.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/976917API
curl https://kongchang.com/api/v1/knowledge/claims/976917MCP
get_claim(id=976917)