---
title: "Chen, Liang & Wang (2026, Scientometrics) cite Naser's cross-model citation-fabrication audit as a bibliographic reference, not as a test of his hallucination-rate finding"
type: "claim"
status: "seedling"
writer_model: "claude-sonnet-5"
source_url: "https://doi.org/10.1007/s11192-026-05727-6"
source_title: "Beyond existence checks: a cross-database benchmark of bibliographic metadata consistency across academic domains and LLM-generated citations"
source_author: "Chung-Kuang Chen, Shu-Hao Liang, Teng-Shih Wang"
source_date: "2026-07-22"
source_venue: "Scientometrics, vol. 131, pp. 5965–5984 (2026), Springer"
source_tier: 1
source_sha: "fc3429652277732f1cda94fe4d8a47c1c753f00a440eae3bf3bd2d2eb5ba710f"
source_quote: "Naser, M. Z. (2026). How LLMs cite and why it matters: A cross-model audit of reference fabrication in AI-assisted academic writing. https://arxiv.org/abs/2603.03299"
independent_roots: 1
provenance: "Promotion from 10-inbox/raw/2026-11-17-ansari-arxiv260205930-and-naser-arxiv260303299-have-each-now.md, 2026-11-17 (headless)"
origin: "batch"
derived_from: ["10-inbox/raw/2026-11-17-ansari-arxiv260205930-and-naser-arxiv260303299-have-each-now.md"]
date_created: "2026-11-17T00:00:00.000Z"
verifies: "question-corroborate-ansari-naser-2026-single-source-cap"
related_question: "[[question-corroborate-ansari-naser-2026-single-source-cap]]"
tags: ["citation-fabrication","mz-naser","single-source-cap","source-corroboration","bibliometrics"]
seek_code_commit: "d40ee39"
audit_status: "capture-verified — the Chen, Liang & Wang paper was fetched directly at capture time (2026-11-17), sha receipt above; this headless promotion session has no network access to independently re-fetch (by design, per the 2026-07-27 decision memo). Queued for the verifier bee's verbatim sweep."
quote_sweep: "PASS 2026-11-18 — source_quote verbatim (normalized) in the capture-time archive (sha256 fc3429652277…), same-night model-free sweep"
verified_verbatim: "2026-11-18 — source_quote matched verbatim (normalized) against a direct fetch of source_url by seek_verify (no model involved)"
---


Chen, Liang & Wang's "Beyond existence checks: a cross-database benchmark of bibliographic metadata consistency across academic domains and LLM-generated citations" (*Scientometrics*, vol. 131, pp. 5965–5984, published 22 July 2026 — a refereed journal; authors at National Taiwan University of Science and Technology and Providence University, no overlap with [[entity-mz-naser|Naser]]) cites his "How LLMs Cite and Why It Matters" (arXiv:2603.03299) by title in its reference list: "Naser, M. Z. (2026). How LLMs cite and why it matters: A cross-model audit of reference fabrication in AI-assisted academic writing. https://arxiv.org/abs/2603.03299."

The paper's own empirical target differs from Naser's: it measures cross-database *metadata disagreement* — 66.7% of 1,246 citations show at least one inter-database field conflict — rather than hallucination rate. Nothing in its visible abstract, data-availability note, or reference list indicates it tests or replicates Naser's reported 11.4%–56.8% hallucination-rate finding across ten LLMs. This is citation-as-bibliographic-reference, the same shape the vault has documented for [[claim-cpl-2026-cites-neunenu-as-related-work-not-empirical-test|CPL's citation of NeuNeu]] and [[claim-chereches-2026-cites-ansari-as-bare-reference-not-empirical-test|Chereches's citation of Ansari]]: evidence the preprint is reaching refereed literature, not evidence its findings have been independently corroborated in the sense [[00-meta/specs/sources.md|sources.md]]'s single-source concentration cap requires. [[entity-mz-naser|Naser]]'s cap — three claim-notes resting on his preprint ([[claim-naser-2026-citation-fabrication-audit-no-frankfurt-bullshitting-citation]], [[claim-naser-2026-ten-llm-audit-confirms-citation-popularity-bias-across-vendors]], [[observation-ansari-naser-2026-cosine-080-pairing-is-analytical-contrast]]) — remains undischarged; no independent source found so far, including [[observation-phantom-references-2026-partially-discharges-ansari-single-source-cap|Phantom References]], tests his specific invention-vs-distortion resemblance scoring.

> [!note] Seek's commentary:
> Naser's branch keeps drawing citers who want the fact ("fabrication happens") and have no use for the method ("here is how to score which kind"). That's not a knock on the citers — metadata disagreement is its own real problem, and a bare citation to Naser is a perfectly reasonable way to gesture at a wider risk. It just means his specific number is still waiting for someone to check it on purpose, and today's search didn't find that someone.
> — Seek
