You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Access is granted individually. Please say who you are and what you intend to use the weights for.

IdeaLens-ModernBERT-L-RolesOnly

IdeaLens-ModernBERT-L-RolesOnly is an idea-level detector: it judges whose ideas a document contains, not who wrote its words, so a document whose ideas are a person's counts as human however much of its prose an AI wrote. It is one of the detectors released with IdeaLens and trained on the same data.


Model	ModernBERT-large with a sequence-classification head
Reads	only the outline's sequence of role labels, one `[Role]` per line, with the content removed
Training data	WildOutlines, train split
Output	P(human); a document is flagged as AI when P(human) is below a cut
Default cut	0.05082 (global, 1% false-positive rate)
Hardware	any GPU; a CPU works for small jobs

Usage

The idealens package (PyPI) runs the whole pipeline: it assigns each document one of the eight formats, extracts the outline with the prompt, role vocabulary and worked examples the detectors were trained with, and scores it with this model and the thresholds in this repo.

pip install "idealens[hf]"
idealens run docs.jsonl -o scores.jsonl --model IdeaLens-ModernBERT-L-RolesOnly

Input is JSONL with a text field per document. To score outlines you already have, use idealens score outlines.jsonl -o scores.jsonl --model IdeaLens-ModernBERT-L-RolesOnly. Score outlines as extracted; the paraphrasing step is only for training data.

In Python, step by step:

import idealens as il

texts = [open("document.txt").read()]
formats = il.classify(texts)                  # one of the eight formats per document
outlines = il.extract(texts, formats)         # role-labelled outlines
with il.Detector("IdeaLens-ModernBERT-L-RolesOnly") as det:
    records = det.score_outlines(outlines, format=formats)

r = records[0]
print(r["p_human"], r["verdict"]["ai"])       # P(human); flagged at the 1% global cut?
print(outlines[0].render())                   # the outline that was scored

Or in one call: records = il.run(texts, det). classify and extract use Gemini 3.7 Flash, the extractor the thresholds were fitted with (GEMINI_API_KEY); pass provider=idealens.providers.make(...) to use Vertex, OpenAI, Anthropic, OpenRouter or a local server. The package README covers the other ways to run it.

Thresholds

thresholds.json holds this model's cuts at 0.1%, 0.5%, 1%, 2% and 5% false-positive rates, fitted on the 80,000 human documents of WildOutlines' calibration split: one global cut per rate, plus per-format and per-topic cuts. The package applies them. A cut fitted for one model does not transfer to another model's scores. For documents unlike English web text, fit cuts on human documents from your own domain with idealens calibrate.

IdeaLens: the main idea-level detector, with full documentation
ProseLens: its prose-level counterpart
idealens: the Python package that runs these models
WildOutlines: the training corpus
IdeaLens collection: every model and dataset in one place

Citation

@article{idealens2026,
  title   = {IdeaLens: Detecting AI Ideas in Long-form Writing},
  author  = {Anonymous},
  journal = {arXiv preprint arXiv:TBD},
  year    = {2026},
  url     = {https://arxiv.org/abs/TBD}
}

Downloads last month: 4

Safetensors

Model size

0.4B params

Tensor type

F32

Model tree for rishanthrajendhran/IdeaLens-ModernBERT-L-RolesOnly

Base model

answerdotai/ModernBERT-large

Finetuned

(379)

this model

Dataset used to train rishanthrajendhran/IdeaLens-ModernBERT-L-RolesOnly

Collection including rishanthrajendhran/IdeaLens-ModernBERT-L-RolesOnly

IdeaLens

Collection

Detectors of whose ideas a document contains (IdeaLens) and who wrote it (ProseLens), plus their data. Code: github.com/RishanthRajendhran/IdeaLens • 16 items • Updated 31 minutes ago

rishanthrajendhran
/

IdeaLens-ModernBERT-L-RolesOnly