Alice

Model · Token classification

open-text-detector-qwen36-35b-a3b-oct10-gguf

Alice

GGUF files of the Open Text Detector token classifier, the model that scores every paper on opentextdetector.com. It detects AI-written and AI-edited text in English research papers, at the level of single tokens and sentences. These files are the LoRA adapters of woog/open-text-detector-qwen36-35b-a3b-oct10 (final-moe, Oct 10, 2026) merged into Qwen/Qwen3.6-35B-A3B (revision 995ad96), converted with llama.cpp (commit 3e390af18d) and quantized. This is not a chat model. Text generation is not what it was trained for. The GGUF gives the final hidden state of every token; the included token head (tokenhead.safetensors, one linear layer from 2,048 to 2 outputs) turns each hidden state into a…

Dataset · Text classification

open-text-detector-papers

Alice

Full text of 125,153 machine-learning papers extracted from their PDFs: conference and journal submissions from OpenReview (accepted, rejected and withdrawn where public), used by Open Text Detector. - clean (default): the text layer after cleanup (positioned-clean-v2: hyphenation, headers/footers, page numbers and similar layout artefacts removed). - direct: the raw positioned text layer from poppler (pdftotext -bbox-layout), with page-level tesseract OCR only for pages without a usable text layer. method says which. - omissions: the clean text with non-prose content replaced by markers: figure text, tables, display equations, garbled inline math, number runs and the reference list.…