Unverified50% confidenceBenchmarkExact time
On the Spider structured generation task, with a candidate budget of 16, the prefetcher covered 96.6% of Qwen3-8B's verification results.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/26/2026
First Seen
Valid until: 1/24/2027
Sources
Related Entities
Related Claims
UnverifiedOn the Spider dataset, schemagate tied with the same model (Claude Sonnet 4.5) at 93.0; the paper's best result on Spider came from DeepSeek V3.2-Reasoning at 95.9.64% similarUnverifiedOn the held-out compound recipe test set, the LoRA fine-tuned model caught 66%, while the base Qwen3.5-4B model caught 78%.64% similarUnverifiedIn schemagate's benchmark, on the Spider dataset's 1034 questions the pure mathematical ranking accuracy is 80.3%, and 96.5% after re-ranking; on the BIRD dataset's 1534 questions the pure mathematical ranking is 88.6%, and 96.7% after re-ranking.64% similarUnverifiedIn a speculative decoding test using Qwen2.5 0.5B as the draft model proposing 4 tokens at a time, the overall draft acceptance rate was 32.9% for serial processing and 37.1% for concurrent processing.62% similarUnverifiedQwen 3 4B's tool calls are correct, but it outputs about 35KB of thinking content per step, so under a six-step budget answering a $215 sales question takes over four minutes.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098259API
curl https://kongchang.com/api/v1/knowledge/claims/1098259MCP
get_claim(id=1098259)