Unverified50% confidenceFactExact time
The BharatSynthQA dataset separately released 300 manually annotated question-answer pairs as a reference set.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOf the 141 submissions, 103 were community contributions, 15 were official acceptance reports, and 25 were kernel validations.60% similarUnverifiedIn a prototype dataset containing 45 real coding-agent sessions, there were 102,233 records, 20,577 tool executions, and 2,336 interaction segments between humans and agents.54% similarUnverifiedThe research team manually annotated 100 real recording cases, labeling 348 scoring units and 162 localization events across ten combined label types.54% similarUnverifiedThe engineering summary in this report is built upon more than 40,000 production training jobs.52% similarUnverifiedMTEB ranks 162 embedding models on 58 datasets across 8 task types.52% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1155342API
curl https://kongchang.com/api/v1/knowledge/claims/1155342MCP
get_claim(id=1155342)