From d5e38fb958403563bf90e884d96660731b1e0379 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Tue, 10 Feb 2026 21:41:48 +0000 Subject: Add dual-vector separation analysis to notes - z_long correlates with long-term prefs (p=0.006), z_short does not (p=0.586) - This confirms dual-vector design: z_long=stable identity, z_short=transient context Co-Authored-By: Claude Opus 4.6 --- notes.md | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/notes.md b/notes.md index 4cf5fd4..5864092 100644 --- a/notes.md +++ b/notes.md @@ -78,7 +78,22 @@ | z_short | 0.010 | 0.681 | 0.586 | | combined | 0.046 | 0.054 | 0.003 | -→ z_long捕获长期偏好趋势最好，z_short基本无信号 +### Dual-vector 分工验证 + +z_short 不和长期 preference Jaccard 相关是**符合预期的**： + +| | z_long | z_short | +|--|--------|---------| +| 设计目的 | 长期稳定偏好 | 短期上下文/噪声吸收 | +| 和长期偏好 Jaccard 相关 | **Yes (p=0.006)** | No (p=0.586) | +| 解读 | 捕获了用户身份 | 没有捕获长期身份（正确） | + +- Jaccard 衡量的是整个 60 sessions 的 revealed preferences 集合 → 长期稳定偏好 +- z_short 设计目的是捕捉当前 session 的短期上下文（如"这轮做 Python"vs"上轮做数学"），本应是 transient 的 +- z_long 和长期偏好显著相关而 z_short 不相关 → 证明 dual-vector 分工有效 + +**报告说法**: +> The dual-vector design effectively separates stable user preferences from transient session context. z_long significantly correlates with long-term preference similarity (p<0.05), while z_short does not — confirming that z_long captures enduring user identity and z_short absorbs session-specific noise as intended. **可视化**: `collaborativeagents/results/fig_main_results.png` panel (c) -- cgit v1.2.3