Unverified50% confidenceFactExact time
The sparse mapping between features can explain 0.85 of a graph's energy on its active features, but when another seed's graph retains only its own features, this proportion drops to 0.47.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen a feature is set to zero, the proportion of next-layer features crossing the truncation threshold reaches as high as above 0.74, and these crossing events carry most of the energy of the response.69% similarUnverifiedBecause the experiment used temperature=0 and a fixed seed in a single deterministic run, any field flip moves the score by about 2.8 percentage points out of 12 tasks × 3 fields = 36 units, so the gap between 91.7% and 83.3% cannot be directly generalized into a statistically meaningful general advantage.65% similarUnverifiedAveraged over 3 random seeds at the same learning rate, good views (two different descriptions of the same photo) reached 0.320, bad views (a single description with some words masked) reached 0.192, and next-word prediction reached 0.148.63% similarUnverifiedIn practice, models in the 78.0 range often perform solidly on factual neutrality but are weak on axes such as intersectionality or double standards, because when two demographic parameters interact the model has less training signal to rely on.62% similarUnverifiedThe same scaffold raised the weak model's execution quality from 0.88 to 2.0 (across four scoring dimensions), yet pushed the strong model toward overcautious shutdown (all four dimensions dropped).62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129404API
curl https://kongchang.com/api/v1/knowledge/claims/1129404MCP
get_claim(id=1129404)