Lishu: A Real-Source Research Workbench for Elite Business Journal Search, Analysis, and Writing Support

Chuang Zhao, Hongke Zhao, Yichen Li, Xiaoquan Zhi, Songyue GuoarXiv 2026 · arXiv

TL;DR

Lishu is an open-source, lightweight research workbench tailored specifically for business school researchers navigating elite journal pools like UTD-24 and FT50. By combining live metadata retrieval with lightweight analytics and optional LLM support, it bridges the gap between finding papers and synthesizing them into actionable research material.

What Problem Does This Paper Address?

Business school researchers, doctoral students, and lab managers live and die by elite journal lists—most notably the UTD-24 and the Financial Times 50 (FT50)—for tenure, promotion, and institutional rankings. However, the actual workflow around these lists is highly fragmented.

General academic search engines like Google Scholar offer massive breadth but lack domain-specific filtering, while static journal directories offer curation but no live search capabilities. Researchers are left to manually scan multiple publisher sites, making it labor-intensive to track emerging topics, compare themes, or transition from a list of search results to actual writing tasks like literature reviews or grant proposals.

Table 1: Problem Context and Artifact Response

Methods

The authors designed Lishu using a lean, low-cost client-server architecture explicitly meant for easy deployment by small labs or individual researchers. Instead of maintaining a massive, expensive proprietary database, Lishu acts as an intelligent orchestration layer.

Figure 1: System architecture of the Lishu research workbench artifact

When a user enters a query, the Node.js backend dynamically executes the following pipeline:

  1. Journal Filtering: Restricts the search boundary strictly to the curated UTD-24/FT50 pools.
  2. Live Retrieval & Enrichment: Fetches real-time metadata from the Crossref REST API and OpenAlex, then checks for open-access full-text availability via Unpaywall and CORE.
  3. Normalization & Analytics: Standardizes the data into a unified schema and uses browser-side tools (like ECharts) to instantly compute topic distributions, affiliation rankings, and method signals.
Figure 2: Search-to-insight workflow

Additionally, Lishu integrates an optional Large Language Model (LLM) layer to support downstream writing tasks, such as generating literature review drafts, simulating virtual peer reviews, and drafting grant proposals.

Datasets

Lishu does not utilize traditional machine learning training datasets. Instead, it operates on live scholarly infrastructure. It integrates and curates data from:

  • UTD-24 and FT50 official journal lists (encompassing 51 unique elite journals).
  • Crossref REST API & OpenAlex for live paper-level metadata, citations, and author affiliations.
  • Unpaywall & CORE for open-access location resolution and full-text excerpt previews.

Key Insights and Ideas

  • The Value of "Middle-Layer" Systems: Lishu proves that academic tools don't need to compete with Google Scholar or Scopus on a global scale to be highly valuable. By narrowing the scope to a specific domain's evaluative logic, a tool can deliver much higher workflow relevance.
  • Source Transparency Over Opaque Scraping: Rather than using black-box data aggregation, Lishu explicitly exposes DOIs, source notes, and official submission links. This maintains strict data provenance, which is vital for academic trust.
  • Lean Infrastructure is Sustainable: By avoiding heavy front-end frameworks (using vanilla HTML/CSS/JS) and leveraging free-tier public hosting (Render) and persistence (Supabase), the authors demonstrate that digital research infrastructure can be maintained on a near-zero budget.

Key Results

The authors successfully developed and deployed Lishu as a fully functioning web artifact. The system successfully unifies 51 top-tier business journals into a single interface. Qualitatively, it effectively compresses the "query-to-insight" pipeline: instead of just delivering a list of links, it provides immediate situational awareness through automated hotspot extraction (e.g., grouping papers into categories like AI/Algorithms or Strategy/Organization) and structural analytics, significantly reducing the cognitive load required for exploratory literature synthesis.

Limitations and Future Work

Because Lishu relies entirely on live external APIs, its performance and data completeness are inherently bound to the timeliness and quality of Crossref and OpenAlex. Furthermore, its current hotspot extraction relies on rule-based heuristics rather than formal, deep topic modeling, and it lacks comprehensive citation-network exploration.

Crucially, the artifact has not yet undergone formal user evaluation. The authors note that future work will focus on conducting task-based user studies with faculty and doctoral students, implementing richer analytics (like co-author networks), and adapting the same lightweight architecture to adjacent fields like finance, operations, or information systems.

Summary updated

Abstract

This paper presents Lishu, a deployable web artifact for searching, monitoring, and interpreting literature from elite business and management journals. The system integrates the UTD-24 and Financial Times 50 (FT50) journal pools and combines Crossref, OpenAlex, Unpaywall, and optional CORE enrichment to support a broader research workflow than article retrieval alone. In the current implementation, users can search across curated journal pools, apply multi-journal filters, preview open full-text excerpts when available, generate citations and exports, inspect topic and affiliation structure, produce review drafts, simulate virtual peer review, and assemble grant-oriented research narratives. Unlike static journal directories or general-purpose academic search engines, the artifact is explicitly scoped to high-status management outlets and is designed to support sensemaking tasks that matter to researchers, doctoral students, and lab managers: identifying recent work, surfacing topical concentration, comparing themes, and converting search output into actionable research material. Architecturally, the system emphasizes source transparency, modularity, and low-cost public deployability through a lightweight Node.js service layer, a multi-page client interface, optional large-language-model enhancement for interpretation and writing support, and a free-tier persistence path through Supabase. The paper contributes both a functioning design artifact and an extensible architectural pattern for journal-pool-specific scholarly discovery and writing support, with implications for digital research infrastructure in information systems and business scholarship.
BibTeX
@misc{zhao2026lishu,
  author = {Chuang Zhao and Hongke Zhao and Yichen Li and Xiaoquan Zhi and Songyue Guo},
  title = {{Lishu: A Real-Source Research Workbench for Elite Business Journal Search, Analysis, and Writing Support}},
  year = {2026},
  eprint = {2604.07934},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.07934},
}
Figure