

















Abstract:Editors and reviewers are expected to ensure that manuscripts cite relevant, accurate, current, and ethically appropriate literature, yet manuscript-level citation auditing remains largely manual, fragmented, and difficult to scale. Citation context, metadata quality, self-citation patterns, and bibliographic integrity all affect whether a reference appropriately supports a local claim. We present CitePrism, a transparent hybrid decision-support framework for editorial citation auditing that combines LLM-assisted contextual reasoning, embedding-based semantic similarity, metadata verification, integrity-oriented flags, and human-in-the-loop analyst review. CitePrism extracts citation neighborhoods, enriches reference metadata, computes fused relevance scores, surfaces metadata and self-citation review prompts, and supports configurable threshold-based triage. In a preliminary validation on a single case-study manuscript with 104 references from pavement engineering, agreement with human binary relevance labels reached Cohen's kappa = 0.429. At operating threshold tau = 17, CitePrism flagged all human-labeled irrelevant citations, while also producing false positives requiring analyst review. These results suggest that CitePrism may support conservative editorial screening and citation-quality triage, but they do not establish general editorial performance. CitePrism is intended as pilot-stage decision support, not as an autonomous misconduct detector or automated editorial decision system. Broader validation across manuscripts, domains, annotators, baselines, and deployment settings is required before operational use.
| Comments: | 30 pages, 5 main figures, 3 tables, appendices with interface screenshots and implementation details; pilot-stage framework and single-manuscript validation study |
| Subjects: | Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL) |
| ACM classes: | H.3.7; H.3.3; I.2.7 |
| Cite as: | arXiv:2605.16000 [cs.SI] |
| (or arXiv:2605.16000v2 [cs.SI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.16000 arXiv-issued DOI via DataCite |
From: Mehrdad Jalali [view email]
[v1]
Fri, 15 May 2026 14:31:45 UTC (973 KB)
[v2]
Tue, 26 May 2026 09:06:21 UTC (2,414 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。