personalization-user-model.git/collaborativeagents, branch main

Add all-methods comparison table with dataset caveat

2026-02-11T01:13:48+00:00

- Add vanilla/contextual/all_memory from fullscale (different datasets)
- Flag dataset mismatch (5-dataset vs 3-dataset)
- Queue matching-dataset vanilla/contextual experiment
- Same-dataset comparison: rag_vector leads in success (54.2%)

Co-Authored-By: Claude Opus 4.6

Add dual-vector ablation experiment (z_short/z_long necessity)

2026-02-11T00:21:34+00:00

- Add rag_vector_no_short (eta_short=0) and rag_vector_no_long (eta_long=0) configs
- Add ablation run script for 60p60s experiment
- Document ablation design and expected results in notes

Co-Authored-By: Claude Opus 4.6

Update (c): two-bar bottom/top 25% comparison, p=0.021*

2026-02-10T21:38:06+00:00

Cleaner than quintile bins - no non-monotonic issue

Co-Authored-By: Claude Opus 4.6

Update (c) to use z_long only: Q5 vs Q1 p=0.006**

2026-02-10T21:34:29+00:00

Co-Authored-By: Claude Opus 4.6

Update main figure: quintile mean+SE bar chart for vector similarity

2026-02-10T21:31:11+00:00

- (c) replaced boxplot with mean+SE bars + trend line, much clearer
- Q5 vs Q1 p=0.003**, clear ascending trend across quintiles

Co-Authored-By: Claude Opus 4.6

Add main results figure for report

2026-02-10T21:28:26+00:00

- (a) RAG+Vector vs Reflection: only rag_vector, clear improvement bars
- (b) Vector growth over 60 sessions
- (c) Preference similarity quartile boxplot (Q4 vs Q1 p=0.018*)

Co-Authored-By: Claude Opus 4.6

Add clean report-ready figures

2026-02-10T21:24:54+00:00

- fig_method_comparison: normalized improvement vs reflection + learning curve
- fig_vector_analysis: vector growth + cumulative head-to-head advantage

Co-Authored-By: Claude Opus 4.6

Add visualization figures for report

2026-02-10T21:18:36+00:00

- learning_and_vectors.png: learning curve, vector growth, cumulative advantage, efficiency
- method_comparison_bars.png: success/effort/timeout bar charts
- vector_similarity_60s.png: PCA, pref-vector correlation (r=0.046, p=0.054), heatmap
- vector_similarity_30s.png: same for 30 sessions
- vector_analysis.png: norm distribution + session range bars

Co-Authored-By: Claude Opus 4.6

Add RAG rewrite, 60-session experiment scripts, and analysis tools

2026-02-10T20:16:36+00:00

- RAG rewrite adapter and vector preference pipeline in personalized_llm
- 60-session experiment queue scripts (reflection, rag, rag_vector, rag_rewrite)
- Vector-preference correlation analysis and visualization scripts
- Local reward model batch processing improvements
- Updated CLAUDE.md with full experiment documentation and notes

Co-Authored-By: Claude Opus 4.6

Add 200 user profiles dataset (43 preferences each)

2026-01-31T07:05:08+00:00

Co-Authored-By: Claude Opus 4.5