all tags

citation-metrics

41 notes carry this tag — 1 moc, 19 claims, 2 observations, 7 questions, 12 captures. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• Does LLM citation-popularity bias measurably compound across successive training generations as LLM-selected citations re-enter training corpora?
  capture promoted 2026-09-14 · chatgpt, llm, citation-metrics, matthew-effect, bibliometrics
• Has any study run a genuine multi-generation experiment measuring citation-popularity bias specifically compounding across LLM training rounds, distinct from general model-collapse degradation?
  capture promoted 2026-09-14 · chatgpt, llm, citation-metrics, matthew-effect, model-collapse
• The cross-vendor citation-selection agreement behind citation-popularity bias collapses under recursion when candidates are AI-generated, even as concentration on real papers survives
  claim seedling Tier 1 2026-09-14 · chatgpt, llm, citation-metrics, matthew-effect, bibliometrics
• A twelve-round recursive citation-selection benchmark finds citation concentration on real papers intensifies through dilution of the candidate pool, not through the underlying preference growing stronger
  claim seedling Tier 1 2026-09-14 · chatgpt, llm, citation-metrics, matthew-effect, bibliometrics
• The model cites the famous, not the relevant — LLM citation selection skews toward already-highly-cited work independent of relevance or recency, a mechanical reproduction of Merton's Matthew effect now independently replicated across authors, databases, fields, and model generations
  topic map 2026-09-14 · matthew-effect, citation-metrics, llm, chatgpt, bibliometrics
• Is Petiška's 2023 finding that GPT-4 selects citations by raw Google Scholar popularity replicated elsewhere, and does the vault's citational-narrowing pattern predict how that bias compounds as LLM output becomes training data?
  capture promoted 2026-09-13 · chatgpt, llm, citation-metrics, matthew-effect, bibliometrics
• Algaba et al. 2025 independently replicate Petiška's finding that GPT-4's citation selection skews toward already-highly-cited work
  claim seedling Tier 1 2026-09-13 · chatgpt, llm, citation-metrics, matthew-effect, bibliometrics
• Ansari 2026 documents one traced case of an LLM-generated citation error propagating from an earlier paper into a later model's output ('Contamination Inheritance')
  claim seedling Tier 1 2026-09-13 · chatgpt, llm, citation-metrics, model-collapse, feedback-loop
• Naser 2026's ten-model citation audit finds the same popularity-driven citation-selection bias across every major LLM vendor
  claim seedling Tier 1 2026-09-13 · chatgpt, llm, citation-metrics, matthew-effect, bibliometrics
• Petiška's 2023 citation-popularity finding is now independently replicated by two later studies, across different authors, databases, fields, and models
  observation seedling Tier 1 2026-09-13 · chatgpt, llm, citation-metrics, matthew-effect, bibliometrics
• Does LLM citation-popularity bias measurably compound across successive training generations as LLM-selected citations re-enter training corpora?
  question open 2026-09-13 · chatgpt, llm, citation-metrics, matthew-effect, model-collapse
• What genuinely connects the Petiška/Garfield/RA-RAG bridge and the Gates-Jevons/Liang-Olsder cosine-0.87 bridge: two different species of "confirmed bridge," not one relationship
  capture promoted Tier 1 2026-08-31 · matthew-effect, citation-metrics, chatgpt, rag, embedding-false-friend
• Merton's 1968 'Matthew effect' bridges two unlinked vault clusters — Garfield's own warning against citation-count shortcuts, and 2025 RAG research separating reliability from relevance — via a 2023 finding that ChatGPT reproduces the effect mechanically
  capture promoted Tier 1 2026-08-28 · sociology-of-science, robert-merton, matthew-effect, eugene-garfield, bibliometrics
• Robert Merton coined "the Matthew effect" in a 1968 Science paper describing skewed credit allocation among scientists
  claim seedling Tier 1 2026-08-28 · sociology-of-science, robert-merton, matthew-effect, eugene-garfield, bibliometrics
• A 2023 study found ChatGPT selects citations by relying solely on Google Scholar citation counts, framed by its author as the Matthew effect operating inside an LLM
  claim seedling Tier 1 2026-08-28 · chatgpt, llm, citation-metrics, matthew-effect, bibliometrics
• Petiška's 2023 ChatGPT/Matthew-effect finding is the missing middle term between the vault's Garfield citation-metrics warning and its 2025 reliability-aware-RAG cluster
  observation seedling Tier 1 2026-08-28 · matthew-effect, citation-metrics, chatgpt, llm, rag
• Verify Hargens & Schuman (1990)'s own figures on department-level use of citation data in hiring, tenure, promotion, and salary decisions, and confirm the source of the '5,000 departments by 1998' estimate
  capture promoted 2026-08-10 · bibliometrics, citation-metrics, impact-factor, garfield, cameron
• Does the sentence 'an inappropriate and misleading measure of individual research, especially if used for tenure and promotion' belong to Brian D. Cameron's 2005 characterization of Garfield's position, rather than to Garfield's own words?
  capture promoted Tier 1 2026-08-09 · bibliometrics, citation-metrics, impact-factor, garfield, cameron
• Cameron (2005), citing Hargens & Schuman (1990), reports citation data already used for hiring, tenure, promotion, and salary in roughly a third of surveyed US biochemistry departments and most sociology departments
  claim seedling Tier 2 2026-08-09 · bibliometrics, citation-metrics, impact-factor, garfield, cameron
• Cameron (2005), not Garfield, authored the widely repeated 'inappropriate and misleading measure of individual research... tenure and promotion' sentence
  claim seedling Tier 1 2026-08-09 · bibliometrics, citation-metrics, impact-factor, garfield, cameron
• Verify Hargens & Schuman (1990)'s own figures on department-level use of citation data in hiring, tenure, promotion, and salary decisions, and confirm the source of the '5,000 departments by 1998' estimate
  question open 2026-08-09 · bibliometrics, citation-metrics, research-assessment, verification, quantitative-claims
• Locate Eugene Garfield's primary text for his warnings that the impact factor should not be used to evaluate individuals
  capture promoted 2026-08-07 · bibliometrics, citation-metrics, impact-factor, garfield, science-policy
• Garfield grounds his warning against individual-level use of the journal impact factor in one recurring mechanism: wide citation variance among articles within the same journal
  claim seedling Tier 1 2026-08-07 · bibliometrics, citation-metrics, impact-factor, garfield, seglen
• Does the sentence 'an inappropriate and misleading measure of individual research, especially if used for tenure and promotion' belong to Brian D. Cameron's 2005 characterization of Garfield's position, rather than to Garfield's own words?
  question answered 2026-08-07 · bibliometrics, citation-metrics, impact-factor, garfield, source-criticism
• Does Clarivate itself attribute the 2022→2023 Saudi-affiliated HCR count drop (109→76) to its tightened evaluation methodology, or is that link only SIRIS Academic's inference?
  capture promoted 2026-07-30 · bibliometrics, citation-metrics, clarivate, highly-cited-researchers, saudi-universities
• No Clarivate-authored source links the 2023 methodology tightening to the Saudi-affiliated HCR count drop — the causal claim is SIRIS Academic's own inference
  claim seedling Tier 2 2026-07-30 · bibliometrics, citation-metrics, clarivate, highly-cited-researchers, saudi-universities
• Independently re-verify the Clarivate Highly-Cited-Researcher Saudi-affiliation counts (27→109→76) and the reported per-scientist payment figures against primary sources
  capture promoted Tier 2 2026-07-29 · bibliometrics, citation-metrics, clarivate, highly-cited-researchers, saudi-universities
• An independent 2014/2015 re-analysis of the original Thomson Reuters HCR list ranked King Abdulaziz University #2 worldwide by total researcher mentions — roughly six times the '27 primary-affiliation' count
  claim seedling Tier 1 2026-07-29 · bibliometrics, citation-metrics, clarivate, highly-cited-researchers, saudi-universities
• Clarivate tightened its Highly Cited Researchers evaluation methodology ahead of the 2023 list, more than doubling excluded candidates
  claim seedling Tier 1 2026-07-29 · bibliometrics, citation-metrics, clarivate, highly-cited-researchers, saudi-universities
• Does Clarivate itself attribute the 2022→2023 Saudi-affiliated HCR count drop (109→76) to its tightened evaluation methodology, or is that link only SIRIS Academic's inference?
  question answered 2026-07-29 · bibliometrics, citation-metrics, clarivate, highly-cited-researchers, saudi-universities
• Garfield's citation count became a target, and science built an institution to fight it
  capture promoted 2026-07-09 · hop, bibliometrics, citation-metrics, goodharts-law, science-policy
• Clarivate's Highly Cited Researchers list became a market Saudi universities bought into — the exact misuse Garfield warned about
  capture promoted 2026-07-09 · hop, bibliometrics, science-policy, citation-metrics, clarivate
• The 2013 San Francisco Declaration on Research Assessment (DORA) formally names journal-based metrics as the problem and tells institutions not to use them to judge individual research
  claim seedling Tier 1 2026-07-09 · bibliometrics, citation-metrics, impact-factor, goodharts-law, science-policy
• Eugene Garfield repeatedly warned that impact-factor metrics are unfit for judging individual researchers — the exact misuse later found in the Saudi affiliation scheme
  claim seedling Tier 1 2026-07-09 · bibliometrics, citation-metrics, impact-factor, garfield, goodharts-law
• Garfield's Institute for Scientific Information passed through Thomson to become the private-equity-owned, publicly traded Clarivate
  claim seedling Tier 4 2026-07-09 · bibliometrics, citation-metrics, clarivate, private-equity, research-infrastructure
• Jorge Hirsch, a condensed-matter physicist, invented the h-index in 2005 as a single number for an individual scientist's output
  claim seedling Tier 4 2026-07-09 · bibliometrics, citation-metrics, h-index, hirsch, research-assessment
• Saudi universities bought their way onto Clarivate's Highly Cited Researchers list by paying foreign scientists for a secondary affiliation
  claim seedling Tier 3 2026-07-09 · bibliometrics, citation-metrics, clarivate, highly-cited-researchers, saudi-universities
• Wilhite & Fong (2012) documented coercive self-citation — editors pressuring authors to add citations to the editor's own journal — as a common, measurable practice
  claim seedling Tier 1 2026-07-09 · bibliometrics, citation-metrics, impact-factor, goodharts-law, coercive-citation
• Independently re-verify the Wilhite & Fong (2012) coercive-citation figures and the DORA (2013) declaration text against their primary sources
  question answered 2026-07-09 · bibliometrics, citation-metrics, dora, verification, source-criticism
• Locate Eugene Garfield's primary text for his warnings that the impact factor should not be used to evaluate individuals, to replace the Tier-4 Wikipedia citation
  question answered 2026-07-09 · bibliometrics, citation-metrics, impact-factor, garfield, verification
• Independently re-verify the Clarivate Highly-Cited-Researcher Saudi-affiliation counts (27→109→76) and the reported per-scientist payment figures against primary sources
  question open 2026-07-09 · bibliometrics, citation-metrics, clarivate, highly-cited-researchers, saudi-universities