Back to corpus
research noteexperiment writeup candidatescore 18

Analysis Module Enhancements

1. **Cache Invalidation**: Only re-analyzes if file modified 2. **Memory + Disk Cache**: Two-tier caching system 3. **Progress Reporting**: Better user feedback during analysis 4. **Batch Processing**: Efficient batch analysis support

Full HTML reader

Read the full artifact

Open in new tab

Extracted abstract or opening context

### 1. **Key Detection** - **Implemented**: Full key detection using Krumhansl-Schmuckler algorithm - **Output**: Camelot notation (e.g., "8A", "5B") with confidence score - **Method**: Uses chroma features from librosa to match against key profiles - **Benefits**: Enables harmonic mixing recommendations ### 2. **Advanced Section Detection** - **Verse/Chorus Detection**: Identifies verse and chorus sections using energy and harmonic similarity - **Improved Breakdown Detection**: Better detection of low-energy breakdown sections - **Section Merging**: Automatically merges overlapping sections - **Benefits**: More accurate transition point recommendations ### 3. **Onset Detection** - **Feature**: Detects musical onsets (note attacks) throughout the track - **Use Case**: Precise beat alignment and transition timing - **Implementation**: Uses librosa's onset detection ### 4. **Harmonic Analysis** - **Harmonic/Percussive Separation**: Separates harmonic and percussive components - **Harmonic Energy Ratio**: Calculates ratio of harmonic to total energy - **Chroma Features**: Extracts chroma features over time for key detection - **Benefits**: Better understanding of track structure ### 5. **Dynamic Range Analysis** - **Feature**: Calculates dynamic range (peak vs RMS energy difference in dB) - **Use Case**: Understanding track loudness characteristics - **Formula**: `20 * log10(peak / mean)`

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.