REVIEW 4 cited by
Technical Report on the Pangram AI-Generated Text Classifier
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present Pangram Text, a transformer-based neural network trained to distinguish text written by large language models from text written by humans. Pangram Text outperforms zero-shot methods such as DetectGPT as well as leading commercial AI detection tools with over 38 times lower error rates on a comprehensive benchmark comprised of 10 text domains (student writing, creative writing, scientific writing, books, encyclopedias, news, email, scientific papers, short-form Q&A) and 8 open- and closed-source large language models. We propose a training algorithm, hard negative mining with synthetic mirrors, that enables our classifier to achieve orders of magnitude lower false positive rates on high-data domains such as reviews. Finally, we show that Pangram Text is not biased against nonnative English speakers and generalizes to domains and models unseen during training.
Forward citations
Cited by 4 Pith papers
-
StoryScope: Investigating idiosyncrasies in AI fiction
StoryScope extracts narrative features showing AI stories favor tidy plots and over-explain themes while human stories show more moral ambiguity and temporal complexity, enabling strong detection and attribution.
-
Experimental Evidence on the Learning Impact of Generative AI
Off-the-shelf generative AI access raises student knowledge-test scores by 0.27 SD immediately and one week later, with delayed unaided essay gains concentrated among students who use AI to explain concepts rather tha...
-
Pangram 4 Technical Report
Pangram 4 is a commercial MoE-based detector claiming 0.9916 AUROC, 0.0041% FPR, 0.3396% FNR, plus tokenwise human/AI-assisted/AI-generated labels and humanizer detection.
-
Team DACTYL at PAN 2026: Bayesian Data Mixing and Empirical X-risk Minimization for AI-text Detection
A Bayesian-uncertainty text filter, partial-AUROC training, and MCGrad calibration produce the second-ranked AI-text detector (0.974 mean score) on the PAN 2026 leaderboard.
Discussion (0). Sign in to comment.