Unverified50% confidenceBenchmarkExact time
In a local test on an NVIDIA DGX Spark, Embedding Gemma 2 indexed 300 animal photos and hit 165 out of 200 retrieval queries, achieving an accuracy of 82.5%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
UnverifiedThe author validated the approach using a toy dataset consisting of 30 real dog images, 10 reasonable new-breed dog images, and 60 poisoned samples pointing toward the attacker's target.60% similarUnverifiedThe study employed a fixed animal-number prompting protocol to measure each dimension separately on the Llama-3.1 series (from 8B to 70B).58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/984064API
curl https://kongchang.com/api/v1/knowledge/claims/984064MCP
get_claim(id=984064)