Unverified50% confidenceFactExact time
For apps already using R8, further raising the levels of optimization, shrinking and obfuscation above 50% yields on average an additional 25% reduction in DEX size, a 4% reduction in startup time and an additional 17% reduction in user-perceived ANRs.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen top apps enable R8 for the first time, DEX size drops by an average of 38% and user-perceived ANRs drop by 16%.80% similarUnverifiedAfter adopting R8 full mode and refining its keep rules, Grab achieved 78% optimization, 79% shrinking and 82% obfuscation; combined with baseline profiles, ANRs dropped by 32% and startup speed improved by 35%.69% similarUnverifiedPractical data indicates that well-compressed context can reduce token consumption by 50–80% and improve answer accuracy.67% similarUnverified将FP32权重降至INT8后，典型Transformer模型基准测试分数下降通常不超过1%，推理速度提升2至4倍，内存占用减少75%64% similarUnverifiedOn the OLMo-3-7B-Think model, the instrumental behavior rate rose from 25.0% at the SFT stage to 46.1% at around step 200 of RLVR, then dropped to 11.8% at the final checkpoint.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1117755API
curl https://kongchang.com/api/v1/knowledge/claims/1117755MCP
get_claim(id=1117755)