Unverified50% confidenceBenchmarkExact time
The transfer experiments in the study show that fine-tuning on the same dataset yields performance gains ranging from +6.8 to +23.1 percentage points.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 6.13-point adversarial drift exceeds the adversarial gains reported in five of the six papers the researchers surveyed.75% similarUnverifiedCompared with single-step models of the same parameter count, Spatial-TRM's context accuracy improves by 44.0% relatively and 9.02 percentage points absolutely.71% similarUnverifiedMETR follow-up experiment data: the returning-developer group showed -18% speedup with a confidence interval of -38% to +9%; newly recruited developers showed -4% speedup with a confidence interval of -15% to +9%, and both confidence intervals cross zero.70% similarUnverifiedIn the experiment, unit completion accuracy increased from 72.4% to 84.9%, a gain of 12.5 percentage points.69% similarUnverifiedThe 7 models that passed the surrogate test had a change rate of 15.9%, while the 6 models that did not pass had a rate as high as 25.8%, indicating that better-performing models are less susceptible to interference but still more so than the effect of prompt modification.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084497API
curl https://kongchang.com/api/v1/knowledge/claims/1084497MCP
get_claim(id=1084497)