Unverified50% confidenceBenchmarkExact time
On the SentiCoref dataset, an "oracle" experiment shows that if all errors among the 10% most uncertain predictions could be corrected without harming correct predictions, Macro-F1 could improve by 9.14 points.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFine-tuned DistilBERT achieves F1=0.9993 on in-distribution testing, but loses 12.9 mean average precision points under topic shift, a greater degradation than the linear model's 5.2 points.75% similarUnverifiedOn unperturbed simulated scenes, strict scoring (greedy center-distance matching) gives precision = recall = F1 = 1.000 with zero false positives.73% similarUnverifiedThe Expected Calibration Error (ECE) increased in seven out of eight event pairs, and in affected scenarios, 12%–51% of the area was confidently mislabeled by the model with near-zero accuracy.71% similarUnverifiedDeepInfer's speculative decoding scheme first estimates the probability of each guess being accepted, tilts the verification budget toward more promising ones, and dynamic verification reduces the number of checks per step by about 30% while the average accepted length stays basically unchanged, raising online throughput by 6%; as the sequence count increases from 16 to 96, the gain climbs from negative 1.5% all the way to 11%.70% similarVerifiedWhen samples are severely imbalanced, Accuracy becomes misleading—a model that predicts everyone as healthy can still achieve an accuracy of over 99%.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130542API
curl https://kongchang.com/api/v1/knowledge/claims/1130542MCP
get_claim(id=1130542)