Unverified50% confidenceBenchmarkExact time
Ablation experiments show that, at the same precision, soft-label hierarchical retention keeps 751% more candidate words than strict power gating, expanding the candidate pool from 41 words to 349 words.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA bag-of-words baseline can pass approximately 41% of the core set, indicating that some test cases contain lexical-level shortcuts.73% similarUnverifiedResearch from institutions including Stanford University shows that for short texts under 200 words, the false positive rate of existing detectors can be as high as tens of percentage points.72% similarUnverifiedOn 162 SciFact long queries, just two random terms can cover 19.9% of the eligible terms and still produce a 39.5% Hybrid target exposure rate.71% similarUnverifiedAblation analysis shows that fine-tuning on the segment paradigm yields a +5.29-point improvement on the test set, while replacing the first 4,500 transcript words with 2,000 retrieved words yields only a +1.55-point improvement.69% similarUnverifiedFor small team sites, the keyword difficulty threshold is usually around 40, and words exceeding this value should be cut directly.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134113API
curl https://kongchang.com/api/v1/knowledge/claims/1134113MCP
get_claim(id=1134113)