| --- |
| title: Dali |
| emoji: ⚖️ |
| colorFrom: gray |
| colorTo: blue |
| sdk: static |
| pinned: true |
| --- |
| |
| # Dali |
|
|
| ### The open verification layer for AI |
|
|
| Dali is the open verification layer for AI: it creates, scores, and preserves evidence so AI-assisted outputs can be independently verified, exchanged, and replayed. Legal AI is the proving ground. |
|
|
| --- |
|
|
| ## Open Artifacts |
|
|
| **[Dali Open Evidence Corpus](https://huggingface.co/datasets/yenklabs/open-evidence-corpus)** · *available* |
| Cross-jurisdiction seed evidence for reproducible research. |
|
|
| **[Dali Citation Benchmark (Seed Sample)](https://huggingface.co/datasets/yenklabs/dali-citation-benchmark)** · *available* |
| 5 hand-curated cases, 14 authorities — methodology review sample (not the full run). |
|
|
| **[Dali Verification Taxonomy](https://huggingface.co/datasets/yenklabs/dali-verification-taxonomy)** · *available* |
| Shared vocabulary for classifying verification outcomes. |
|
|
| **[Full evaluation run](https://github.com/yenklabs/Dali/tree/main/data/results)** · *available* |
| 524 citations · 3 models · 5 jurisdiction tracks — on GitHub `data/results/`. |
|
|
| **[Evidence Infrastructure](https://github.com/yenklabs/Dali)** · *available (early-stage v0.2.1)* |
| Open verification engine, methodologies, and reproducible evaluation workflows. |
|
|
| --- |
|
|
| ## Quick Start |
|
|
| ```python |
| from datasets import load_dataset |
| |
| dataset = load_dataset("yenklabs/open-evidence-corpus") |
| ``` |
|
|
| --- |
|
|
| **[GitHub](https://github.com/yenklabs/Dali)** · **[Contribute](https://github.com/yenklabs/Dali/blob/main/CONTRIBUTING.md)** · **[yenklabs.com](https://yenklabs.com)** |
|
|
| --- |
|
|
| ## Research models (roadmap) |
|
|
| Lightweight, reproducible research models — not foundation models. All *planned*. |
|
|
| | Release | Model | Purpose | Status | |
| |---------|-------|---------|--------| |
| | v0.1 | Dali Verification Taxonomy Classifier | Predict standardized verification outcome labels | planned | |
| | v0.2 | Dali Citation Risk Classifier | Estimate citation verification risk from evidence metadata | planned | |
| | v0.3 | Dali Authority Matching Baseline | Reproducible baseline for authority matching experiments | planned | |
| | v0.4 | Dali Proposition Support Classifier | Classify proposition support relationships for legal authorities | planned | |
|
|
| --- |
|
|
| ## Ecosystem |
|
|
| | Layer | Status | |
| |-------|--------| |
| | **Datasets** — Open Evidence Corpus, Citation Benchmark seed sample, Verification Taxonomy | available | |
| | **Full evaluation run** — 524 citations on [github.com/yenklabs/Dali/data/results](https://github.com/yenklabs/Dali/tree/main/data/results) | available | |
| | **Models** — Taxonomy Classifier, Citation Risk, Authority Matching, Proposition Support | planned | |
| | **Spaces** — Evidence Explorer, Benchmark Dashboard, Citation Verification Demo | planned | |
| | **Future datasets** — Evaluation Prompts, Replay Corpus, Evidence Artifacts | planned | |
|
|
| > Dali is the open verification layer for AI: it creates, scores, and preserves evidence so AI-assisted outputs can be independently verified, exchanged, and replayed. |
|
|
