Unverified50% confidenceFactExact time
The SurvICL team built a survival analysis benchmark covering 103 datasets, the largest survival analysis benchmark to date.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedThe researchers selected 159 multi-turn BFCL V4 tasks with complete precise replay paired data for the main analysis.57% similarUnverifiedCOCO is a standard benchmark dataset for object detection and segmentation tasks, containing over 330,000 images and 80 categories.55% similarUnverifiedThe dataset comes from the team's open-source NAP (Neutrae Agent Platform) project; 72 valid logs were filtered from 2,893 raw sessions, ultimately constructing 38 fine-grained scenario matrices.54% similarUnverifiedSynAM-E contains 85 physically calibrated event data segments from 15 data sources across 8 institutions.54% similarUnverifiedThe research team released a multi-perspective dataset called NormReact, containing 450 norm violation scenarios.53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042084API
curl https://kongchang.com/api/v1/knowledge/claims/1042084MCP
get_claim(id=1042084)