README.md

---
license: other
license_name: openmdw-1.1
license_link: LICENSE
base_model: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
library_name: transformers
language:
- en
tags:
- ai-text-detection
- prose-provenance
datasets:
- rishanthrajendhran/WildOutlines
extra_gated_prompt: "Access is granted individually. Please say who you are and what you intend to use the weights for."
---

# ProseLens

ProseLens detects **who wrote the words** of a document. It is IdeaLens's counterpart in the paper: the same
backbone, training documents and labels, but it reads the raw document text instead of an outline, so it learns
word-level provenance. It returns P(human), the probability that the document was written by a person.

ProseLens is `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16` fine-tuned with LoRA (rank 64) on 1M English web
documents ([WildOutlines](https://huggingface.co/datasets/rishanthrajendhran/WildOutlines)).

## Results

From the paper: ProseLens is accurate when a document's ideas and words come from the same source (99.1%), but
when they come from different sources it tracks the words and reaches 25.4% on idea provenance. IdeaLens, trained
identically on outlines, reaches 95.3% and 81.3%; Pangram 4 reaches 98.5% and 25.9%.

## Usage

Pass the document text as is.

### Quick start with the idealens package

[idealens](https://github.com/RishanthRajendhran/IdeaLens) ([PyPI](https://pypi.org/project/idealens/)) scores documents with ProseLens on vLLM and applies the thresholds in this repo. No
outline and no LLM call is needed:

```bash
pip install "idealens[vllm]"
idealens score docs.jsonl -o scores.jsonl --model ProseLens
```

Input is JSONL with a `text` field per document. In Python:

```python
import idealens as il

with il.Detector("ProseLens") as det:         # vLLM, with this repo's thresholds
    records = det.score_documents([open("document.txt").read()])
print(records[0]["p_human"], records[0]["verdict"]["ai"])
```

To compare with idea-level detection on the same documents, `idealens run docs.jsonl -o ideas.jsonl --model IdeaLens`
extracts their outlines and scores them with [IdeaLens](https://huggingface.co/rishanthrajendhran/IdeaLens). The rest
of this section runs the model directly.

### Load the merged model (66 GB download)

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("rishanthrajendhran/ProseLens")
model = AutoModelForCausalLM.from_pretrained("rishanthrajendhran/ProseLens", dtype=torch.bfloat16, device_map="auto").eval()
```

The weights take 59 GiB of GPU memory, and each input adds more; see *Hardware requirements*.

### Or apply the adapter to the base model (3 GB download)

`adapter/` holds the LoRA adapter as trained, in the layout of the Tinker training service. If you already have the
base model, `load_adapter.py` merges the adapter into it in memory. The resulting weights are bit-identical to the
merged model's:

```python
import importlib.util
from huggingface_hub import hf_hub_download

path = hf_hub_download("rishanthrajendhran/ProseLens", "load_adapter.py")
spec = importlib.util.spec_from_file_location("load_adapter", path)
la = importlib.util.module_from_spec(spec); spec.loader.exec_module(la)
model, tok = la.load_model()   # base model + adapter/, then la.p_human(model, tok, text)
```

Do not load `adapter/` with `peft.PeftModel`. In transformers, Nemotron fuses the Mamba gate and x projections into
one `in_proj` and stores each layer's 128 routed experts as a single 3D tensor, so PEFT has nowhere to attach most of
the adapter and skips it without a warning; the model then scores close to the base model. `tinker-cookbook`'s
`weights.build_hf_model` can also merge the adapter into full weights.

### Score a document

ProseLens compares the next-token probabilities of `human` and `ai`:

```python
SYSTEM = "Given a document, answer with one word: human if the document was human-written, ai if it was AI-generated."
SUFFIX = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
HUMAN, AI = 50755, 2464   # token ids of "human" and "ai"

@torch.no_grad()
def p_human(text):
    ids = tok.encode(f"<|im_start|>system\n{SYSTEM}<|im_end|>\n<|im_start|>user\n{text}{SUFFIX}",
                     add_special_tokens=False)
    logits = model(torch.tensor([ids], device=model.device)).logits[0, -1].float()
    return torch.softmax(logits[[HUMAN, AI]], -1)[0].item()

text = open("document.txt").read()
print(p_human(text))
```

Build the prompt string exactly as above rather than through the chat template.

### Score with vLLM

For many inputs, vLLM is about 15 times faster than the code above and fits much longer inputs on one 80 GB GPU.
With vLLM 0.21 (install `xgrammar==0.2.1`; later releases require transformers < 5), reusing `SYSTEM`, `SUFFIX`,
`HUMAN` and `AI` from above:

```python
import math, os
os.environ.setdefault("VLLM_USE_FLASHINFER_SAMPLER", "0")   # FlashInfer kernels compile CUDA code and need nvcc
os.environ.setdefault("VLLM_USE_FLASHINFER_MOE_FP16", "0")
os.environ.setdefault("VLLM_USE_DEEP_GEMM", "0")            # H100 warmup crashes when DeepGEMM is not installed
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

tok = AutoTokenizer.from_pretrained("rishanthrajendhran/ProseLens")
llm = LLM(model="rishanthrajendhran/ProseLens", dtype="bfloat16", max_num_seqs=256, enable_prefix_caching=False,
          max_logprobs=20, enable_flashinfer_autotune=False, seed=0)
sp = SamplingParams(max_tokens=1, temperature=0.0, logprobs=20)

def p_human_batch(texts):
    prompts = [{"prompt_token_ids": tok.encode(f"<|im_start|>system\n{SYSTEM}<|im_end|>\n<|im_start|>user\n{x}{SUFFIX}",
                                               add_special_tokens=False)} for x in texts]
    out = []
    for r in llm.generate(prompts, sp, use_tqdm=False):
        lp = r.outputs[0].logprobs[0]           # the top 20 next-token log-probabilities
        out.append(1 / (1 + math.exp(lp[AI].logprob - lp[HUMAN].logprob)))
    return out

# when done: without this, vLLM 0.21 keeps a script running after its last line
llm.llm_engine.engine_core.shutdown()
```

`max_num_seqs=256` keeps every running sequence's Mamba state in memory; vLLM's H100 default (1,024) does not fit
beside the weights. If `human` or `ai` is missing from the top 20 (rare), score the prompt followed by each label
token with `SamplingParams(max_tokens=1, prompt_logprobs=0)` and read the last prompt log-probability of each.
Scores agree with the training-time scores to about 0.001 in P(human) on average; A100 and H100 GPUs differ by as much.

### Thresholds

ProseLens flags a document as AI-written when P(human) is below a cut. Each cut is set so
that a given share of human documents is flagged (the false-positive rate, FPR), measured on the 80,000 human
documents in WildOutlines's `calibration` split (10,000 per format). The paper's operating point is the global
cut at 1% FPR.

| FPR | 0.1% | 0.5% | 1% | 2% | 5% |
|---|---:|---:|---:|---:|---:|
| Global cut | 0.07082 | 0.30469 | 0.60539 | 0.92502 | 0.99889 |

Per-format cuts give each format its own operating point. They need the document's format, which the paper
assigns with WebOrganizer's annotation prompt run on Gemini 3.7 Flash; the calibration documents use the formats
recorded in WildOutlines. Each is the
format's own quantile, shrunk toward the global cut with weight n / (n + 2500); at 0.1% FPR 10,000 documents
per format are too few, so there is no per-format cut. A document outside these eight formats has no
per-format cut; do not fall back to the global cut for it.

| Format | 0.5% | 1% | 2% | 5% |
|---|---:|---:|---:|---:|
| Nonfiction Writing | 0.14387 | 0.27050 | 0.49499 | 0.93935 |
| Knowledge Article | 0.24236 | 0.38050 | 0.64044 | 0.95295 |
| Personal Blog | 0.68275 | 0.87993 | 0.98163 | 0.99966 |
| News Article | 0.29554 | 0.55535 | 0.90380 | 0.99788 |
| Academic Writing | 0.77788 | 0.89967 | 0.98279 | 0.99969 |
| User Reviews | 0.62135 | 0.85161 | 0.98035 | 0.99964 |
| Personal About Page | 0.41699 | 0.78714 | 0.97730 | 0.99966 |
| Creative Writing | 0.84923 | 0.91749 | 0.98411 | 0.99958 |

`thresholds.json` holds every cut at full precision.

These rates hold for English web documents like the training data. For another domain, fit the cut on
human documents from that domain.

ProseLens scores 97% of human calibration documents above 0.99, so its cuts at higher FPRs sit close
to 1 and small shifts in score move the realised FPR a long way.

## Hardware requirements

Measured with transformers 5.15 in bf16 on NVIDIA H100 80GB GPUs (our other runs used A100 80GB), with transformers'
PyTorch implementation of the Mamba layers (no fused Mamba kernels installed). We have not tried CPU-only inference.

| | Merged model | Adapter route (`load_adapter.py`) |
|---|---|---|
| Download | 65.8 GB | 65.8 GB base model + 3.1 GB adapter |
| Peak CPU RAM while loading | 60 GiB | 60 GiB |
| GPU memory once loaded | 58.8 GiB | 58.8 GiB (66 GiB during the ~10 s it takes to apply the adapter) |

GPU memory then grows with the length of the input, by about 4.2 MiB per token at typical lengths, scoring one
input at a time:

| Input tokens | 500 | 1,000 | 2,000 | 4,000 | 8,000 |
|---|---:|---:|---:|---:|---:|
| Peak GPU memory, one 80 GB GPU | 61.0 GiB | 63.1 GiB | 67.3 GiB | 75.7 GiB | does not fit |
| Peak memory per GPU, two 80 GB GPUs (`device_map="auto"`) | | | | 47.4 GiB | 63.7 GiB |
| Seconds per input, H100 | 0.18 | 0.34 | 0.66 | 1.32 | 2.70 |

Inputs of 6,000 tokens do not fit on one 80 GB GPU and 12,000 do not fit on two; lowering the Mamba chunk size from
128 to 64 did not change either limit.

ProseLens reads whole documents, so their length decides the hardware. One 80 GB GPU handles documents up to about
4,000 tokens (about 3,000 words); 85% of WildOutlines's test documents are that short. Two 80 GB GPUs handle up to
8,000 tokens (about 6,000 words), which covers all but about 1 in 1,000 test documents. We have not measured longer
inputs or more GPUs.

## Intended use and limitations

- ProseLens estimates who wrote a document's words. It should not be the sole basis for decisions about a person's work.
- It was trained on English web documents of at least 500 words in eight long-form formats (Nonfiction Writing, Knowledge Article, Personal Blog, News Article, Academic Writing, User Reviews, Personal About Page, Creative Writing).
- Its training labels come from the Pangram prose detector, applied to whole documents.

## Related models

| Model | Backbone | Reads |
|---|---|---|
| [IdeaLens](https://huggingface.co/rishanthrajendhran/IdeaLens) | Nemotron-3.5-Lightning-30B-A3B, LoRA | outline |
| [ProseLens](https://huggingface.co/rishanthrajendhran/ProseLens) (this model) | Nemotron-3.5-Lightning-30B-A3B, LoRA | document text |
| [IdeaLens-NoParaphrase](https://huggingface.co/rishanthrajendhran/IdeaLens-NoParaphrase) | Nemotron-3.5-Lightning-30B-A3B, LoRA | outline, trained without paraphrasing |
| [IdeaLens-Qwen3.5-9B](https://huggingface.co/rishanthrajendhran/IdeaLens-Qwen3.5-9B) | Qwen3.5-9B, classification head | outline |
| [IdeaLens-ModernBERT-L](https://huggingface.co/rishanthrajendhran/IdeaLens-ModernBERT-L) | ModernBERT-large | outline |
| [ProseLens-ModernBERT-L](https://huggingface.co/rishanthrajendhran/ProseLens-ModernBERT-L) | ModernBERT-large | document text |
| [IdeaLens-LogisticClassifier](https://huggingface.co/rishanthrajendhran/IdeaLens-LogisticClassifier) | logistic regression over text-embedding-3-large | outline |
| [IdeaLens-ModernBERT-L-NoParaphrase](https://huggingface.co/rishanthrajendhran/IdeaLens-ModernBERT-L-NoParaphrase) | ModernBERT-large | outline, trained without paraphrasing |
| [IdeaLens-ModernBERT-L-RolesOnly](https://huggingface.co/rishanthrajendhran/IdeaLens-ModernBERT-L-RolesOnly) | ModernBERT-large | role labels only |
| [IdeaLens-Qwen3.5-9B-PerItem](https://huggingface.co/rishanthrajendhran/IdeaLens-Qwen3.5-9B-PerItem) | Qwen3.5-9B, classification head | single outline items, pooled |
| [IdeaLens-ModernBERT-L-PerItem](https://huggingface.co/rishanthrajendhran/IdeaLens-ModernBERT-L-PerItem) | ModernBERT-large | single outline items, pooled |
| [IdeaLens-LogisticClassifier-PerItem](https://huggingface.co/rishanthrajendhran/IdeaLens-LogisticClassifier-PerItem) | logistic regression over text-embedding-3-large | single outline items, pooled |

Training data: [WildOutlines](https://huggingface.co/datasets/rishanthrajendhran/WildOutlines).

All IdeaLens models and datasets are in the [IdeaLens collection](https://huggingface.co/collections/rishanthrajendhran/idealens-6abee785ce6196fc0be9200f).

## License

OpenMDW-1.1, the license of the base model (see `LICENSE`).

## Citation

```bibtex
@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}
}
```