Back to corpus
technical noteexperiment writeup candidatescore 40
NKoMathLab - Project Handoff Document
**Generated:** 2026-05-31 **Project:** NKoMathLab - Educational Mathematics App for N'Ko Speech/Gesture Systems **Handoff To:** Codex (or continuation agent) **Handoff From:** OpenCode (qwen3.5:397b)
Full HTML reader
Read the full artifact
Extracted abstract or opening context
**Generated:** 2026-05-31 **Project:** NKoMathLab - Educational Mathematics App for N'Ko Speech/Gesture Systems **Handoff To:** Codex (or continuation agent) **Handoff From:** OpenCode (qwen3.5:397b)
NKoMathLab is a **comprehensive educational mathematics application** built in SwiftUI for iOS. It teaches the mathematical foundations underlying:
- **FAC** (Featural Acoustic Coding) - Speech feature extraction system - **N'Ko** - West African writing system with tonal syllables (3,024 entries) - **AirDeck** - Gesture-based DJ control system - **Computational Choreography** - Body motion as computation - **Anticipatory Transformers** - Predictive sequence models
- **11 comprehensive lessons** written (5,000-10,000+ words each) - **iOS app built and deployed** to simulator - **All core files created** with full educational content - **Ready for user testing** and content expansion
| # | Lesson | Topic ID | Status | Word Count | Key Concepts | |---|--------|----------|--------|------------|--------------| | 1 | Vectors & Geometry | `vectors-geometry` | ✅ Complete | ~8,000 | Dot product, cosine similarity, projection, FAC/N'Ko mappings | | 2 | SVD/PCA | `svd-pca` | ✅ Complete | ~9,000 | Eigenvectors, dimensionality reduction, codebook compression | | 3 | Optimization | `optimization` | ✅ Complete | ~9,000 | Gradient descent, SGD, Adam, loss function ethics | | 4 | Fourier Analysis | `fourier-thinking` | ✅ Complete | ~10,000 | DFT/FFT, STFT, spectrograms, mel filterbanks | | 5 | Speech Acoustics | `speech-acoustics` | ✅ Complete | ~10,000 | Source-filter model, formants, F0, VOT, N'Ko tones | | 6 | Phonetics & Features | `phonetics-features` | ✅ Complete | ~9,000 | Distinctive features, feature geometry, FAC extraction | | 7 | Probability | `probability` | ✅ Complete | ~8,000 | Bayes' theorem, distributions, Bayesian recognition | | 8 | Information Theory | `information-theory` | ✅ Complete | ~8,000 | Entropy, mutual information, KL divergence, cross-entropy | | 9 | Sequence Models | `sequence-models` | ✅ Complete | ~9,000 | HMMs, Viterbi, forward-backward, CTC, tone HMMs | | 10 | Dynamical Systems | `dynamical-systems` | ✅ Complete | ~9,000 | State space, attractors, stability, bifurcations, motor control | | 11 | Transformers | `transformers` | ✅ Complete | ~10,000 | Attention, multi-head, positional encoding, speech transformers |
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.