Unverified50% confidenceReleaseExact time
The research team publicly released the evaluation harness, a fine-tuned 4B tool-selection model, and all evaluation trajectories.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/17/2026
First Seen
Valid until: 2/15/2027
Sources
Related Entities
Related Claims
UnverifiedThe research team tested four deployed open-weight models through VERA's requirements pipeline.75% similarUnverifiedThe study proposes a heterogeneity-driven team selection framework whose core is to characterize each model through offline profiling.75% similarUnverifiedThe research team designed five behavioral probes to test models' ability to satisfy hierarchical constraints.75% similarUnverifiedThe research team evaluated over 35 compressed checkpoints across six open-weight models, covering the two mainstream method categories of quantization and pruning.74% similarUnverifiedThe researchers developed an evaluation framework comprising five complementary metrics: VCR, Model-Harness Fit, Cross-Model Fit, Interaction Residuals and Token Load.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1178348API
curl https://kongchang.com/api/v1/knowledge/claims/1178348MCP
get_claim(id=1178348)