[
    {
        "id": "osp-24263",
        "type": "article-journal",
        "title": "Team MSU GenText-Forensics Challenge 2026 Technical Report",
        "author": [
            {
                "family": "Koltsov",
                "given": "Kirill"
            },
            {
                "family": "Gushchin",
                "given": "Aleksandr"
            },
            {
                "family": "Vatolin",
                "given": "Dmitriy"
            },
            {
                "family": "Antsiferova",
                "given": "Anastasia"
            }
        ],
        "URL": "https://omanscience.com/en/articles/team-msu-gentext-forensics-challenge-2026-technical-report",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Document text forgery has evolved beyond simple pixel-level manipulation: modern attacks alter not only the appearance of a document but also its meaning, and increasingly target the OCR & LLM pipelines that consume such documents. The ACM MM 2026 GenText-Forensics challenge therefore requires systems that not only decide whether a multilingual text image is forged, but also localize the point of manipulation, identify the attack type, and produce a human-readable forensic report with supporting evidence. We present our solution, a decomposed chain-of-thought (CoT) pipeline that combines a document tampering detector (DTD) with two Qwen3-VL-32B vision-language models, each LoRA-adapted to a distinct sub-task. DTD produces tampering probability maps that are converted into numbered candidate regions; a first model (the Filterer) validates these regions and assigns a preliminary forgery type, while a second model (the Semantic Detective) merges and re-grounds the surviving regions, searches for purely semantic anomalies that are invisible to pixel-level detectors, and writes the final report. Both models are trained by distilling chain-of-thought traces from a privileged Qwen3-VL-235B teacher that has access to ground-truth masks and reports. Our approach secured third place in the ACM MM 2026 GenText-Forensics challenge. We describe the data preparation, test-time augmentation, region rendering, distillation protocol, and training configuration in detail, and report ablations over detector thresholds, prompt designs, and pipeline decompositions."
    }
]