Back to corpus
technical noteexperiment writeup candidatescore 40

Session Handoff — March 22-24, 2026

Second pass found 8 additional issues: 1. Phantom author "Dedhia" inconsistency 2. Author initial mismatches across papers 3. Remaining internal references (Supabase, Graph Kernel, port numbers) 4. 19+ "we/our" pronouns in paper.md 5. "(full context, full context)" copy-paste error 6. "9-step pipeline" header but 11 steps listed 7. V5 still referenced in limitations section 8. AI slop: "transcends", "Additionally"

Open full HTMLDownload HTMLCorpus JSONPaper schema

Full HTML reader

Read the full artifact

Open in new tab

Extracted abstract or opening context

## Overview 12+ hour session across March 22-24. Primary focus: research paper evaluation, Anticipatory Transformer build + GPU training, BEYOND daemon, OpenAI Parameter Golf submission, repo cleanup for public scrutiny. ### Experiment 1: Anticipation Geometry Enhanced Eval - **What**: Does anticipation beat embeddings on conversation convergence prediction? - **Data**: 50K turns from Supabase, 126 conversations with strict labels (55 converged, 71 not) - **Result**: Anticipation-only 63.5% vs Embedding PCA 52.8% vs Combined 65.0% vs Baseline 56.3% - **Key features (95% bootstrap CI excludes zero)**: - `c_final` (final commitment): 69.8%, r=-0.372 - `tp_mean` (mean transition pressure): 69.8%, r=-0.196 - `rm_mean` (mean recovery margin): 61.9%, r=-0.203 - `emb_dist_mean`: 62.7%, r=+0.163 - **Permutation test**: p=0.175 (not significant at 0.05, need ~200+ conversations) - **Script**: /tmp/definitive_eval.py (ran on Mac1) - **Results file**: Desktop/Comp-Core/papers/evaluation-results/definitive-eval.json ### Experiment 2: Domain Shift (Paper 3) - **What**: Does frozen KG degrade on newer data while live KG maintains coverage? - **Data**: 354K+ turns from Supabase, 356 entities from Graph Kernel - **Result**: Frozen KG coverage drops 100% → 66.5% over 3 periods. Live KG stays 100%. - **Cohen's d**: 1.226 (coverage), 1.295 (path availability) - **Results file**: Desktop/Comp-Core/papers/evaluation-results/domain-shift-results.json and domain-shift-experiment.json ### Experiment 3: Computational Choreography Demo - **What**: Full pipeline proof — sensor → anticipation scalars → Strudel audio parameters - **Output**: 3-panel dark-themed visualization at Desktop/computational-choreography/demo/demo_output.png - **Script**: Desktop/computational-choreography/demo/demo_pipeline.py - **Strudel output**: Desktop/computational-choreography/demo/strudel_output.js (11 keyframes) - **Key finding**: Transition pressure spikes at exact motion phase boundaries ### Experiment 4: KARL Ablation - **What**: Do top-35 high-advantage trajectories differ measurably from random? - **Data**: 290 trajectories from Desktop/karl/karl/trajectories.jsonl - **Result**: Cohen's d = 3.065 (massive). Top-35 reward 0.768 vs Random-35 0.637 - **Tool entropy**: 2.012 vs 0.891 (2.3x more diverse) - **Success rate**: 100% vs 95.8% - **Results file**: [home-path]

Promotion decision

What has to happen next

Attach run IDs, datasets, metrics, and reproduction commands.

Why this is not always a full paper yet

Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.