mlsanityData to 14 Oct 2026

Pangram 4 Technical Report

arXiv 2607.27183 ↗First posted 29 Jul 2026cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

We present Pangram 4, the latest deep-learning-based AI-text classification model from Pangram Labs. We achieve an AUROC of 0.9916 with a false positive rate of 0.0041% and a false negative rate of 0.3396%. In addition to its increased overall accuracy compared with Pangram 3, Pangram 4 exhibits superior out-of-distribution generalization and robustness to adversarial attacks. Another novel contribution of Pangram 4 is its improved ability to distinguish fine-grained edits and mixed AI-human co-authored text. We demonstrate improvements to both boundary detection tasks and the detection of interleaved AI assistance. Finally, we report metrics on standard AI detection benchmarks showing that Pangram 4 achieves state-of-the-art performance on the AI text detection task across a wide variety of settings and domains.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 26 of its 55 references that are in the map. First posted on arXiv 29 Jul 2026.

Builds on

26 of 55 references.

References · 26

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  2. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
  3. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 629
  4. 2023GPT detectors are biased against non-native English writerscited by 178
  5. 2025FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Languagecited by 143
  6. 2015Better Summarization Evaluation with Word Embeddings for ROUGEcited by 66
  7. 2024LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?cited by 49
  8. 2025People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated textcited by 40
  9. 2024DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarioscited by 38
  10. 2024Technical Report on the Pangram AI-Generated Text Classifiercited by 34
  11. 2024Beemo: Benchmark of Expert-edited Machine-generated Outputscited by 27
  12. 2025EditLens: Quantifying the Extent of AI Editing in Textcited by 26
14 more
  1. 2025DAMAGE: Detecting Adversarially Modified AI Generated Textcited by 20
  2. 2025Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writingcited by 19
  3. 2024GenAI Detection Tools, Adversarial Techniques and Implications for Inclusivity in Higher Educationcited by 14
  4. 2025Machine-generated text detection prevents language model collapsecited by 14
  5. 2025AI use in American newspapers is widespread, uneven, and rarely disclosedcited by 10
  6. 2026StoryScope: Investigating idiosyncrasies in AI fictioncited by 9
  7. 2026Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceablecited by 6
  8. 2026The Impact of AI-Generated Text on the Internetcited by 6
  9. 2026Retrieval Collapses When AI Pollutes the Webcited by 4
  10. 2026Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviewscited by 3
  11. 2026'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptionscited by 3
  12. 2026TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing Practicescited by 2
  13. 2026MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Textcited by 1
  14. 2026Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text Detectioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Toward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Persuasioncited by 0
  2. 2026Agents Can Use Base Models to Evade AI Detectioncited by 0
  3. 2026Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writingcited by 0