Unverified50% confidenceBenchmarkExact time
In the NASA Kepler signal classification test, Jev achieved an overall accuracy of 72.5% across all 8,054 decisions, consistent with NASA archive labels.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/21/2026
First Seen
Valid until: 12/20/2026
Sources
Related Entities
Related Claims
VerifiedChain-of-Thought prompting improved PaLM 540B's accuracy on the GSM8K math benchmark from 17.9% to 58.1%.58% similarUnverifiedIn the LongMemEval benchmark, BM25 accuracy improved from 78.8% to 85.2% with 5 chunks.56% similarUnverifiedJev successfully recovered 1,999 out of 2,731 (approximately 73%) confirmed planets in terms of identification.56% similarUnverifiedThe simple 3-rule baseline used for comparison achieved an accuracy of only 64.4%, with Jev leading by approximately 8 percentage points.56% similarUnverifiedThe CAPI-DINO ViT-B/14 model achieved a linear probing accuracy of 68.7% on the iNat21 dataset.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/937907API
curl https://kongchang.com/api/v1/knowledge/claims/937907MCP
get_claim(id=937907)