{
  "abstract": "Financial and economic research often relies on structured supply-chain disclosures and commercial databases. In China, supplier--customer disclosure is typically limited to major partners of listed firms, leaving unlisted firms and long-tail inter-firm links poorly captured in structured data. Public web evidence can partly complement this gap through corporate, government, and trade-media disclosures; however, full-text web mining at scale is costly because pages are often inaccessible or expensive to process with large language models (LLMs). We propose a snippet-driven method for constructing a supply chain knowledge graph (SCKG), with firms as nodes and inter-firm relationships as edges. Web search snippets are query-biased summaries returned with search results. We use them as a scalable first-pass evidence layer for LLM-based relationship extraction. We evaluate the pipeline in terms of extraction efficiency and coverage. For extraction efficiency, exhaustive full-text chunking discovers 19.8$\\times$ more unique relationships than snippets, but requires 251.2$\\times$ more input tokens and yields higher redundancy. For coverage, we use 130,685 Chinese firms as search seeds, covering Shanghai/Shenzhen-listed firms and large unlisted firms as of 2024. In the listed-firm subset, the resulting SCKG covers 7.2$\\times$ more firms and 9.3$\\times$ more relationships than the CSMAR disclosure-based benchmark, while revealing heavy-tailed degree patterns. Retained provenance metadata make the SCKG an auditable complement to disclosure-based databases.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Journal reference: 2026 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), pp. 345-352 (2026)",
  "arxiv": "2605.27845",
  "author_total": 2,
  "authors": [
    {
      "name": "Hiroto Fukada"
    },
    {
      "name": "Takayuki Mizuno"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f78rwnjqvn9fq.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.27845",
  "fulltext_url": null,
  "id": "f78rwnjqvn9fq",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.27845",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.SI"
    ],
    [
      "arxiv",
      "physics.soc-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2605.27845",
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-27",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/f78rwnjqvn9fq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:52Z",
      "native_id": "2605.27845",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.27845"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.soc-ph",
      "subfield": "statistical-nonlinear"
    }
  ],
  "title": "Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China",
  "title_text": "Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:52Z",
  "url": "https://research.draconitic.com/paper/f78rwnjqvn9fq",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1109/cifer67845.2026.11692384",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}