{
  "abstract": "Extracting and correlating knowledge from heterogeneous scientific publications poses a fundamental data engineering challenge for data-driven materials discovery. Traditional keyword search lacks semantic depth, while generic large language models (LLMs) are prone to hallucinated predictions. To address these limitations, we present OptoMatKG, a literature-scale data engineering system whose core contributions are threefold: (1) a domain-specific knowledge graph construction pipeline based on a nine-category fullworkflow ontology; the resulting graph comprises 2.62 million entities and 3.38 million typed relations; (2) a cascaded multi-stage retrieval pipeline that synergistically integrates LLM-based query normalization, semantic vector indexing and Materials Project pre-filtering to enhance metric-aware candidate ranking; and (3) an evidence-constrained auditing module that forces every output to anchor to DOI-supported reasoning chains, thereby enforcing end-to-end hallucination prevention. Using optoelectronic inverse design as a validation testbed, experiments verify that our entity extractor reaches a micro-averaged F1 of 0.971. Comprehensive tests over 2000 real-world queries further demonstrate that our system surpasses keyword-based and singlestage baselines in Recall@K and metric coverage. The system accurately quantifies multi-objective performance trade-offs while ensuring fully traceable inference. Although validated on photodetectors, the proposed solution provides a generalizable, pluggable engineering framework readily extendable to other functional material discovery pipelines.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "Ben Ni"
    },
    {
      "name": "Lei Zhang",
      "orcid": "0000-0001-6873-7314"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c148e7byfkxae.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008315/v1",
  "fulltext_url": null,
  "id": "c148e7byfkxae",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008315/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7208770532",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008315/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-04",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/c148e7byfkxae.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008315",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008315/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "OptoMatKG: A Traceable Knowledge Graph Framework with Semantic Retrieval for Optoelectronic Materials Science",
  "title_text": "OptoMatKG: A Traceable Knowledge Graph Framework with Semantic Retrieval for Optoelectronic Materials Science",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:17Z",
  "url": "https://research.draconitic.com/paper/c148e7byfkxae",
  "venue": "ChemRxiv",
  "versions": []
}