{
  "abstract": "Silicon pixel detector R&D depends on a large and rapidly growing technical literature, including beam-test and irradiation studies, performance measurements, simulation, and design reports. Locating the supporting evidence passage for a measurement, operating condition, or design decision is therefore a computing and data-science challenge for detector-development workflows. General-purpose language models are insufficient unless grounded in traceable primary sources, particularly in a domain with specialised terminology, configuration-dependent measurements, and rapidly evolving experimental results. We address this with a reproducible, general-purpose framework for evidence-grounded retrieval over technical literature, using silicon pixel detector R&D as a demanding validation domain. The framework combines sparse lexical retrieval, dense semantic retrieval, and hybrid reciprocal-rank fusion, with an optional graph-guided exploration layer and grounded, abstention-aware response generation. The accompanying benchmark provides manually curated chunk-level evidence annotations, source-level diagnostics, semantic relevance checks, and negative-query abstention tests over two detector query sets. We evaluate six retrieval configurations across 378 source documents and 8,442 indexed chunks. Hybrid sparse-dense retrieval gives the strongest strict evidence recovery, achieving Hit@5 of 0.917 on the core benchmark and 0.951 on the curated extension benchmark, while graph-based methods are more effective for literature exploration and source discovery. Graph expansion is therefore best employed as a discovery layer over the hybrid retrieval backbone. The framework provides reusable software for traceable, 1 evidence-grounded knowledge access in silicon detector R&D and high-energy physics instrumentation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.24725",
  "author_total": 5,
  "authors": [
    {
      "name": "Tianqi Gao"
    },
    {
      "name": "Ruobing Jiang"
    },
    {
      "name": "Dawei Fu"
    },
    {
      "name": "Qiang Li"
    },
    {
      "name": "Matthew Kenzie"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f7kg8hm33fcbm.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.24725",
  "fulltext_url": null,
  "id": "f7kg8hm33fcbm",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.24725",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.comp-ph"
    ],
    [
      "arxiv",
      "physics.ins-det"
    ],
    [
      "openalex",
      "1710|Information Retrieval and Search Behavior"
    ]
  ],
  "openalex": "W7165797730",
  "pdf_url": "https://arxiv.org/pdf/2606.24725",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/f7kg8hm33fcbm.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:18Z",
      "native_id": "2606.24725",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.24725"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.ins-det",
      "subfield": "applied-instrumentation"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    }
  ],
  "title": "A Reproducible Benchmark and Evidence-Retrieval Software Framework for Silicon Detector R&D Literature",
  "title_text": "A Reproducible Benchmark and Evidence-Retrieval Software Framework for Silicon Detector R&D Literature",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:18Z",
  "url": "https://research.draconitic.com/paper/f7kg8hm33fcbm",
  "venue": "arXiv",
  "versions": []
}