Unverified50% confidenceFactExact time
The team extracted result tables and ablation experiment data from the full texts of 79,000 papers.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
UnverifiedThe research team conducted a retrospective ablation analysis across 12 models with a total of 121,680 valid trials, of which 79,853 failed the executability check.71% similarUnverifiedBy re-tallying the results files, readers found a row of data that the authors had skipped: the maintainer file lists 9 of 212 tests judged WEAK (4%), while the agent file lists 79 of 591 (13%).69% similarUnverifiedThe team's first study collected about 95,000 pieces of AI-cited content and decomposed 189 factors, but it was overturned due to problems such as p > n, using in-sample data for evaluation, and using globally random negative samples; after query-level out-of-fold re-measurement, R² = −0.31.68% similarUnverifiedAmong the approximately 2,000 papers examined, more than 1,100 had at least one key claim independently verified, of which 266 were fully reproduced, 632 were partially reproduced through small-scale experiments, and approximately 4,000 individual claims were confirmed.65% similarUnverifiedThe ThinkingBox benchmark conducted a total of 121,680 trials, of which 79,853 failed.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130075API
curl https://kongchang.com/api/v1/knowledge/claims/1130075MCP
get_claim(id=1130075)