[
    {
        "id": "osp-19406",
        "type": "article-journal",
        "title": "InvestigationWorlds: An Agentic Environment for Legal Investigation",
        "author": [
            {
                "family": "Sun",
                "given": "Albert Yu"
            },
            {
                "family": "Benard",
                "given": "Andrew"
            },
            {
                "family": "Hamilton",
                "given": "Sil"
            },
            {
                "family": "Marcelo",
                "given": "Anna Teresita A."
            },
            {
                "family": "Kim",
                "given": "Yong Jae"
            },
            {
                "family": "Henneking",
                "given": "Carl-Leander"
            },
            {
                "family": "Hu",
                "given": "Rundong"
            },
            {
                "family": "Wang",
                "given": "Yuhong"
            },
            {
                "family": "Mimno",
                "given": "David"
            },
            {
                "family": "Yang",
                "given": "Bishan"
            },
            {
                "family": "Labutov",
                "given": "Igor"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/investigationworlds-an-agentic-environment-for-legal-investigation",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "We introduce InvestigationWorlds, an agentic environment for legal investigation. We build on an underused artifact of U.S. civil litigation: the summary judgment motion. This motion relies upon a record composed of real evidence exhibits, and results in a court-adopted hypothesis that is treated as ground truth for the purposes of deciding the motion. Each environment is built from a real U.S. Federal Court case retrieved from Public Access to Court Electronic Records (PACER) and augmented by an attorney-validated generation pipeline that synthesizes role-tagged documents around the original record. The resulting corpus admits multiple coherent factual readings, only one of which matches the court-adopted hypothesis. Evaluating on 100 cases, we find agents often commit to incorrect hypotheses despite retrieving relevant evidence, struggling to distinguish the court-adopted hypothesis from alternative hypotheses."
    }
]