# SEED: Simple ViT and Evolving Harness for Explainable Text Forgery Detection

arXiv: https://arxiv.org/abs/2606.21138 · HTML: https://mlsanity.com/paper/2606.21138/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [Your ViT is Secretly an Image Segmentation Model](https://mlsanity.com/paper/2503.19108/) (2025)
- [Toward Real Text Manipulation Detection: New Dataset and New Solution](https://mlsanity.com/paper/2312.06934/) (2023)
- [TextShield-R1: Reinforced Reasoning for Tampered Text Detection](https://mlsanity.com/paper/2602.19828/) (2026)
- [An End-to-End Model for Logits-Based Large Language Models Watermarking](https://mlsanity.com/paper/2505.02344/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learning](https://mlsanity.com/paper/2608.04052/) (2026)

## Abstract (arXiv)

AI-assisted image editing threatens trust in financial, legal, and identity records. The GenText-Forensics Challenge at ACM MM 2026 addresses this by requiring structured forensic reports, in which integrating detection, pixel-level localization, and natural language explanation for multilingual text-centric forgery images. We present SEED, a modular system with three components. First, a similarity-guided pipeline augments training with diverse synthetic forgeries. Second, a single ViT, built on DINOv3 with LoRA adaptation, jointly performs detection and pixel-level localization while preserving pre-trained priors with minimal trainable parameters. Third, an evolving harness takes the detector's predictions and generates a complete forensic report via an MLLM, iteratively improved through a proposer-evaluator loop optimizing report quality. SEED ranked 3rd in the GenText-Forensics Challenge. Code and data are available at https://github.com/KahimWong/GenText-Forensics-3rd-Place.