Unverified50% confidenceBenchmarkExact time
The dual-view model achieved an accuracy of 89.9% on the TSExam benchmark.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedOn the TSRBench benchmark, the model using only line graphs achieved an accuracy of 44.5%, while the dual-view model improved it to 53.2%, an improvement of nearly 9 percentage points.72% similarUnverifiedThe dual-view model achieved a numerical accuracy of 86.8% on the multivariate ChatTS alignment task.70% similarUnverifiedThe human baseline accuracy is 90.8%.68% similarUnverifiedBlueVetaUpright achieved 88.2% and 94.0% accuracy in the two test batches respectively, while ChatGPT achieved 82.1% and 69.9% respectively.67% similarUnverifiedIn passages that actually contain dataset citations, precision increases to 89.5%.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041904API
curl https://kongchang.com/api/v1/knowledge/claims/1041904MCP
get_claim(id=1041904)