jimnoneill
/

pub-guard

Text Classification

document-classification

scientific-papers

toxicity-detection

publication-screening

quality-control

Model card Files Files and versions

133 MB

Ctrl+K

Ctrl+K

1 contributor

History: 55 commits

jimnoneill's picture

PDF features with 30%% dropout: page_count, text_density, fonts, aspect_ratio from PosterSentry

aefe8c9 verified 6 months ago

models
Retrained head_toxicity.npz — real poster data, no synthetic junk 8 months ago
pubguard-embedding
Update embedding model cache 7 months ago
scripts
Clean gate script — no errors module dependency 8 months ago
src
Fix gate: only scientific_paper passes 8 months ago
.gitattributes

1.57 kB
Add PubGuard logo 8 months ago
PubGuard.png

2.58 MB
xet

Add PubGuard logo 8 months ago
README.md

7.57 kB
Update README.md 7 months ago
config.json

938 Bytes
Add config.json for HuggingFace download tracking 8 months ago
head_ai_detect.npz
Pickle imports
- No problematic imports detected
What is a pickle import?
4.93 kB
xet

Update head_ai_detect.npz: 3x clean window, bioRxiv boilerplate stripping, 10K abstract search 6 months ago
head_doc_type.npz

22.2 kB
xet

PDF features with 30%% dropout: page_count, text_density, fonts, aspect_ratio from PosterSentry 6 months ago
head_toxicity.npz
Pickle imports
- No problematic imports detected
What is a pickle import?
4.88 kB
xet

Update head_toxicity.npz: 3x clean window, bioRxiv boilerplate stripping, 10K abstract search 6 months ago
pyproject.toml

687 Bytes
Upload pyproject.toml with huggingface_hub 8 months ago