Back to corpus
experimentexperiment writeup candidatescore 18
RAG++ v0 Evaluation Report
- **Action Classification F1:** 84.5% - **Relevance Rate:** 7.7% - **"Oh Wow" Rate:** 0.0% - **Avg Relevance Score:** 2.08/5.0 - **Regime Differentiation:** 16.7% - **Explainability Score:** 82.0%
Full HTML reader
Read the full artifact
Extracted abstract or opening context
- **Action Classification F1:** 84.5% - **Relevance Rate:** 7.7% - **"Oh Wow" Rate:** 0.0% - **Avg Relevance Score:** 2.08/5.0 - **Regime Differentiation:** 16.7% - **Explainability Score:** 82.0%
| Criterion | Target | Status | |-----------|--------|--------| | Action Classification F1 | ≥ 70% (84.5%) | ✅ MET | | Relevance Rate | ≥ 65% (7.7%) | ❌ NOT MET | | "Oh Wow" Rate | ≥ 30% (0.0%) | ❌ NOT MET | | Better than Random | Yes (No) | ❌ NOT MET | | Contextual Awareness | ≥ 50% (16.7%) | ❌ NOT MET |
| Metric | Value | |--------|-------| | Total Users | 1 | | Total Life States | 27 | | Total Transitions | 26 | | Total Life Events | 320 | | Avg Transitions/User | 26.0 | | Date Range | 2025-09-29 to 2025-12-16 |
| Metric | Value | |--------|-------| | Accuracy | 73.3% | | Precision | 95.0% | | Recall | 76.3% | | F1 Score | 84.5% |
| Action Type | Precision | Recall | F1 Score | Support | |-------------|-----------|--------|----------|---------| | ReduceGravity | 100.0% | 87.5% | 93.3% | 8 | | ReduceMass | 80.0% | 57.1% | 66.7% | 7 | | IncreaseAlignment | 100.0% | 85.7% | 92.3% | 7 | | IncreaseThrust | 100.0% | 75.0% | 85.7% | 8 |
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.