Add links to paper, code, and project page
Browse filesHi! I'm Niels from the community science team at Hugging Face. I've updated the model card to include links to the official project page, the GitHub repository (ArtifactBench), and the associated paper. I've also added the dataset metadata for better discoverability. This will help users more easily find the surrounding research and evaluation tools.
README.md
CHANGED
|
@@ -1,17 +1,21 @@
|
|
| 1 |
---
|
| 2 |
-
license: cc-by-nc-4.0
|
| 3 |
-
tags:
|
| 4 |
-
- audio-classification
|
| 5 |
-
- ai-music-detection
|
| 6 |
-
- forensic
|
| 7 |
-
- onnx
|
| 8 |
language:
|
| 9 |
-
|
|
|
|
| 10 |
pipeline_tag: audio-classification
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
# ArtifactNet v9.4 — AI-Generated Music Forensic Detection
|
| 14 |
|
|
|
|
|
|
|
| 15 |
ArtifactNet detects AI-generated music by extracting forensic residual artifacts via a task-specific UNet, rather than learning generator-specific patterns. This approach generalizes across 22 AI music generators with only 4.2M parameters.
|
| 16 |
|
| 17 |
> ⚠️ **License: CC BY-NC 4.0 — Non-Commercial Only**
|
|
@@ -117,4 +121,4 @@ and via the Patent Cooperation Treaty (PCT). The CC BY-NC 4.0 license on this ON
|
|
| 117 |
inference build does **not** convey any patent rights. Commercial use, even under a
|
| 118 |
commercial copyright license, requires a separate patent license. Academic and
|
| 119 |
research use within the scope of CC BY-NC 4.0 is permitted without separate patent
|
| 120 |
-
license, consistent with standard research-use exemptions.
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
+
- en
|
| 4 |
+
license: cc-by-nc-4.0
|
| 5 |
pipeline_tag: audio-classification
|
| 6 |
+
datasets:
|
| 7 |
+
- intrect/artifactbench
|
| 8 |
+
tags:
|
| 9 |
+
- audio-classification
|
| 10 |
+
- ai-music-detection
|
| 11 |
+
- forensic
|
| 12 |
+
- onnx
|
| 13 |
---
|
| 14 |
|
| 15 |
# ArtifactNet v9.4 — AI-Generated Music Forensic Detection
|
| 16 |
|
| 17 |
+
[Paper](https://huggingface.co/papers/2604.16254) | [Code](https://github.com/Intrect-io/artifactbench) | [Project Page](https://demo.intrect.io)
|
| 18 |
+
|
| 19 |
ArtifactNet detects AI-generated music by extracting forensic residual artifacts via a task-specific UNet, rather than learning generator-specific patterns. This approach generalizes across 22 AI music generators with only 4.2M parameters.
|
| 20 |
|
| 21 |
> ⚠️ **License: CC BY-NC 4.0 — Non-Commercial Only**
|
|
|
|
| 121 |
inference build does **not** convey any patent rights. Commercial use, even under a
|
| 122 |
commercial copyright license, requires a separate patent license. Academic and
|
| 123 |
research use within the scope of CC BY-NC 4.0 is permitted without separate patent
|
| 124 |
+
license, consistent with standard research-use exemptions.
|