Post-retraction citation and generative AI: a PubMed search and screening record set

Supporting archive for a narrative review of post-retraction citation and of the reproduction of withdrawn claims by generative AI. It holds the complete, unedited search and screening artefacts of that review: the pooled harvest of 3,345 PubMed records, the seventy-four records read in full, the screening outputs, all thirty-six query strings with their record counts, and the three Python scripts that produced them. The denominator chain (3,345 harvested, 702 notice records removed, 2,643 screened, 155 shortlisted, 74 read in full, 44 cited) can therefore be checked by re-running the deposited scripts and queries rather than by writing to the authors. Records were retrieved from PubMed through the NCBI E-utilities interface; titles and abstracts remain the property of their respective authors and publishers and are deposited here for academic reproducibility. The scripts, the screening outputs and the topic definitions are the authors' own work. Persistent identifier: 10.17605/OSF.IO/3PSGB (OSF project 3psgb).

Authors

Publication Details

Journal
Open Science Framework
Published
2026-11-04
DOI
https://doi.org/10.17605/osf.io/3psgb
Primary Topic
Academic integrity and plagiarism
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Post-retraction citation and generative AI: a PubMed search and screening record set

wenbin tan
Open Science Framework
Academic integrity and plagiarism
article

Post-retraction citation and generative AI: a PubMed search and screening record set

wenbin tan
article en

Abstract

Supporting archive for a narrative review of post-retraction citation and of the reproduction of withdrawn claims by generative AI. It holds the complete, unedited search and screening artefacts of that review: the pooled harvest of 3,345 PubMed records, the seventy-four records read in full, the screening outputs, all thirty-six query strings with their record counts, and the three Python scripts that produced them. The denominator chain (3,345 harvested, 702 notice records removed, 2,643 screened, 155 shortlisted, 74 read in full, 44 cited) can therefore be checked by re-running the deposited scripts and queries rather than by writing to the authors. Records were retrieved from PubMed through the NCBI E-utilities interface; titles and abstracts remain the property of their respective authors and publishers and are deposited here for academic reproducibility. The scripts, the screening outputs and the topic definitions are the authors' own work. Persistent identifier: 10.17605/OSF.IO/3PSGB (OSF project 3psgb).

Open Science Framework
Openalex Percentile: Top 11%
Academic integrity and plagiarism
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Post-retraction citation and generative AI: a PubMed search and screening record set — wenbin tan · Open Science Framework (2026) | TGRS Research Map | TGRS