Unverified50% confidenceBenchmarkExact time
In a benchmark of 30 held-out test windows, TabPFN achieved 100.0% overall accuracy, 100.0% shock recall, 0.33 ms CPU latency, 0.0% step-frequency false alarms, and required no training or tuning.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIn the same reproduction experiment, ResNet-20 achieved a test accuracy of 90.4% and ResNet-56 achieved a test accuracy of 91.7%, with training accuracies of 97.4% and 99.0% respectively.71% similarUnverifiedIn the benchmark, Random Forest (100 trees) achieved 100.0% overall accuracy, 0.19 ms CPU latency, and 0.0% step-frequency false alarms, but required GridSearchCV tuning.71% similarUnverifiedIn the LongMemEval benchmark, BM25 and embedding solutions converge to approximately 95% accuracy at 20 chunks70% similarUnverifiedIn the benchmark test, the heuristic peak rule achieved 93.3% overall accuracy, 100.0% impact recall, and 38.4% cadence false positives, requiring manual threshold tuning.68% similarUnverifiedTabPFN在小规模数据集（<1000样本、<100特征）上已展现出与XGBoost竞争甚至超越的性能67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1007775API
curl https://kongchang.com/api/v1/knowledge/claims/1007775MCP
get_claim(id=1007775)