Expired50% confidenceFactExact time
In the MemoryBench table, the scores of the five models are 85.5, 85.6, 79.0, 81.4, and 81.5 respectively, with a gap of only 0.1 points at the top.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn the specific experimental case, the overlapping-anchor scheme (n=912) showed the model at 55.2% versus the majority class at 51.1%, a net advantage of +4.1pp, about 2.4 standard errors; the non-overlapping-anchor scheme (n=163) showed 59.5% versus 54.0%, a net advantage of +5.5pp, about 1.4 standard errors.68% similarUnverifiedOn the hard tier, recall@5 improved from 0.000 to 0.955 (under default blending weights), and reached 1.000 when using the lower-bound variant.66% similarUnverifiedAll models averaged 0.91 on explicit memory updates but only 0.67 on implicit updates; Opus 5.5 and Gemini 3.1 Pro caught every implicit change, while gpt-oss-20b caught zero.65% similarUnverifiedIn the controlled test, the cache hit rate increased from 76.1% to 85.4%.61% similarUnverifiedThe report's prediction section lists five records, but each retains only a confidence value (0.85%, 0.85%, 0.9%, 0.9%, 0.9%), with all prediction text missing.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034409API
curl https://kongchang.com/api/v1/knowledge/claims/1034409MCP
get_claim(id=1034409)