ideadet-qwen8b-1m-outline
Idea-level AI-text detector. Answers whose ideas a document contains, not who typed the sentences: a document whose ideas are a person's is labelled human however much of the surface an AI produced.
- Backbone: Qwen3.5 8B (7.94 B parameters), sequence-classification head
- Training corpus: 1M
- Reads at inference: a de-leaked (paraphrased) role-labelled outline of the document
Selected checkpoint: step 12056, epoch 0.92.
Stored y=1 means HUMAN. The score is softmax(logits)[:, 0] = P(human), and the detector
fires when that falls below a calibrated threshold. Thresholds are quantiles of the score
distribution over held-out human documents and are not included here: a cut from one model
or input form is meaningless against another's scores.
Fuller documentation and evaluation results to follow.