# Context Loader Test Report
**Generated:** 2026-04-30T08:22:18.941Z
**Source folder:** `D:\Projects\phd\PSEG\pges_toolkit\docs`

## Summary

| Metric | Value |
|---|---|
| Files loaded | 3 |
| Total text chars | 1,00,609 |
| Estimated tokens | ~25,153 |
| Budget used | 62.9% |
| Truncated | true |
| Images | 18 |

## Files (load order)

1. `DACTRL_Experiment_Summary.md`
2. `DACTRL_Summary.md`
3. `DACTRL_Architecture_Methodology.md (partial)`

## Images

| # | File | KB | Description |
|---|---|---|---|
| 1 | `auc_f1_k_curve.png` | 52 | auc f1 k curve |
| 2 | `bootstrap_f1_auc.png` | 97 | bootstrap f1 auc |
| 3 | `c12_waveform_translator.png` | 76 | c12 waveform translator |
| 4 | `c13_hightrials.png` | 132 | c13 hightrials |
| 5 | `c13_three_source.png` | 82 | c13 three source |
| 6 | `c14_honest_k0.png` | 88 | c14 honest k0 |
| 7 | `cross_nucleus_clean.png` | 78 | cross nucleus clean |
| 8 | `cross_nucleus_heatmap.png` | 140 | cross nucleus heatmap |
| 9 | `cross_region_bar.png` | 48 | cross region bar |
| 10 | `da_baselines.png` | 31 | da baselines |
| 11 | `day0_comparison.png` | 84 | day0 comparison |
| 12 | `embedding_tsne.png` | 319 | embedding tsne |
| 13 | `feature_distributions.png` | 444 | feature distributions |
| 14 | `feature_importance.png` | 73 | feature importance |
| 15 | `latency_boxplot.png` | 77 | latency boxplot |
| 16 | `learning_curve.png` | 60 | learning curve |
| 17 | `reliability_diagram.png` | 115 | reliability diagram |
| 18 | `seizure_lifecycle.png` | 164 | seizure lifecycle |

## Context Preview (first 3000 chars)

```
────────────────────────────────────────────────────────────
## SOURCE FILE: DACTRL_Experiment_Summary.md
────────────────────────────────────────────────────────────

# DACTRL — Complete Experiment Summary
**Author:** Bhargava Ganti  
**Date:** April 2026  
**Purpose:** Chronological record of every experiment tried, every combination tested, and what we learned from each.

---

## The Core Problem

**Goal:** Detect Post-Ictal Generalized EEG Suppression (PGES) from thalamic DBS implant recordings (15 patients, ~100 windows each).

**Two fundamental challenges:**
1. **Data scarcity** — 15 thalamic patients is not enough to train a deep learning model from scratch
2. **Domain gap** — large public EEG datasets are scalp-only; thalamic iEEG has different morphology, amplitude, and spectral properties

**Solution hypothesis:** Use large scalp EEG corpora (CHB-MIT: 686 patients, TUH: 29 patients) to pre-train a feature encoder, then adapt to each thalamic patient with a few labeled examples (K-shot ProtoNet).

---

## Data Sources

| Dataset | Type | Size | Notes |
|---|---|---|---|
| CHB-MIT | Scalp EEG | 686 patients | Post-ictal labels inferred (noisy) |
| TUH EEG Corpus | Scalp EEG | 29 patients | Annotator-scored post-ictal (cleaner) |
| PSEG Thalamic | Thalamic SEEG | 15 patients | FBTCS-only, 4 nuclei (CeM, CL, ANT, MD) |

**Simultaneous recordings available with adequate scalp coverage (≥18ch):**  
P2 (CL, 19ch), P10 (ANT, 18ch), P12 (ANT, 19ch)  
*(P6: 2ch scalp — insufficient; P13: excluded from all analyses due to label noise)*

---

## Phase 1 — Biological Validation (Jan–Feb 2026)

### What we did
Validated whether published PGES criteria apply to thalamic recordings. Extracted 11 features from raw EDF files for 15 patients and compared PGES vs baseline distributions.

### What we found — Critical discovery
**Three features are directionally INVERTED in thalamus vs scalp:**

| Feature | Scalp PGES | Thalamic PGES | Why |
|---|---|---|---|
| Suppression Ratio (SR) | HIGH (cortex suppressed) | LOW (thalamus active, driving delta) | Perspective inversion |
| Approx Entropy (ApEn) | LOW (flat signal) | LOW | Same direction (ok) |
| Zero-Crossing Rate (ZCR) | LOW | LOW | Same direction (ok) |

Actually: SR is the key inversion — scalp PGES means flat line (low amplitude → high SR paradoxically via the suppression formula), thalamic PGES means active slow delta (high amplitude → low SR).

**Impact:** Before correction, biological rule had 86.8% false positive rate. After correction: 29.4%.  
**Script:** `verify_biological_rule.py`

---

## Phase 2 — Algorithm Development (Feb–Mar 2026)

### Iteration 1 — v1 FOMAML (Baseline)
**What:** FOMAML (first-order MAML) meta-learning with scalp pre-training (Stage 1) + thalamic LOSO meta-training (Stage 2).  
**Result:** F1=0.765±0.182 (15-patient LOSO, K=10)  
**Script:** Original DACTRL pipeline

---

### Iteration 2 — Training Source Comparison (6 Scenarios)

Testing what data combination drives perf
```