home.social

#scientificfraud — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #scientificfraud, aggregated by home.social.

  1. “fraudulent studies are now appearing at a faster rate than legitimate scientific publications. The authors say the findings should serve as a warning to the scientific community to strengthen safeguards before public trust in science begins to erode”
    #Science #Scicomm #ScientificFraud
    sciencedaily.com/releases/2026

  2. “fraudulent studies are now appearing at a faster rate than legitimate scientific publications. The authors say the findings should serve as a warning to the scientific community to strengthen safeguards before public trust in science begins to erode”
    #Science #Scicomm #ScientificFraud
    sciencedaily.com/releases/2026

  3. “fraudulent studies are now appearing at a faster rate than legitimate scientific publications. The authors say the findings should serve as a warning to the scientific community to strengthen safeguards before public trust in science begins to erode”
    #Science #Scicomm #ScientificFraud
    sciencedaily.com/releases/2026

  4. “fraudulent studies are now appearing at a faster rate than legitimate scientific publications. The authors say the findings should serve as a warning to the scientific community to strengthen safeguards before public trust in science begins to erode”

    sciencedaily.com/releases/2026

  5. “fraudulent studies are now appearing at a faster rate than legitimate scientific publications. The authors say the findings should serve as a warning to the scientific community to strengthen safeguards before public trust in science begins to erode”
    #Science #Scicomm #ScientificFraud
    sciencedaily.com/releases/2026

  6. RE: mathstodon.xyz/@highergeometer

    From now on, my procedure to check papers that are suspicious of being made with AI includes using the search function of my PDF reader and trying to find “**”, and maybe also “__”.

    There might be some false positives in papers about programming languages.

    #AI #ScientificFraud

  7. RE: mathstodon.xyz/@highergeometer

    From now on, my procedure to check papers that are suspicious of being made with AI includes using the search function of my PDF reader and trying to find “**”, and maybe also “__”.

    There might be some false positives in papers about programming languages.

    #AI #ScientificFraud

  8. RE: mathstodon.xyz/@highergeometer

    From now on, my procedure to check papers that are suspicious of being made with AI includes using the search function of my PDF reader and trying to find “**”, and maybe also “__”.

    There might be some false positives in papers about programming languages.

    #AI #ScientificFraud

  9. RE: mathstodon.xyz/@highergeometer

    From now on, my procedure to check papers that are suspicious of being made with AI includes using the search function of my PDF reader and trying to find “**”, and maybe also “__”.

    There might be some false positives in papers about programming languages.

    #AI #ScientificFraud

  10. RE: mathstodon.xyz/@highergeometer

    From now on, my procedure to check papers that are suspicious of being made with AI includes using the search function of my PDF reader and trying to find “**”, and maybe also “__”.

    There might be some false positives in papers about programming languages.

    #AI #ScientificFraud

  11. "Science is characterized by collaboration and cooperation, but also by uncertainty, competition, and inequality. While there has always been some concern that these pressures may compel some to defect from the scientific research ethos—i.e., fail to make genuine contributions to the production of knowledge or to the training of an expert workforce—the focus has largely been on the actions of lone individuals. Recently, however, reports of coordinated scientific fraud activities have increased. Some suggest that the ease of communication provided by the internet and open-access publishing have created the conditions for the emergence of entities—paper mills (i.e., sellers of mass-produced low quality and fabricated research), brokers (i.e., conduits between producers and publishers of fraudulent research), predatory journals, who do not conduct any quality controls on submissions—that facilitate systematic scientific fraud. Here, we demonstrate through case studies that i) individuals have cooperated to publish papers that were eventually retracted in a number of journals, ii) brokers have enabled publication in targeted journals at scale, and iii), within a field of science, not all subfields are equally targeted for scientific fraud. Our results reveal some of the strategies that enable the entities promoting scientific fraud to evade interventions. Our final analysis suggests that this ability to evade interventions is enabling the number of fraudulent publications to grow at a rate far outpacing that of legitimate science."

    #ScientificIntegrity
    #ScientificFraud

    pnas.org/doi/10.1073/pnas.2420

  12. "Science is characterized by collaboration and cooperation, but also by uncertainty, competition, and inequality. While there has always been some concern that these pressures may compel some to defect from the scientific research ethos—i.e., fail to make genuine contributions to the production of knowledge or to the training of an expert workforce—the focus has largely been on the actions of lone individuals. Recently, however, reports of coordinated scientific fraud activities have increased. Some suggest that the ease of communication provided by the internet and open-access publishing have created the conditions for the emergence of entities—paper mills (i.e., sellers of mass-produced low quality and fabricated research), brokers (i.e., conduits between producers and publishers of fraudulent research), predatory journals, who do not conduct any quality controls on submissions—that facilitate systematic scientific fraud. Here, we demonstrate through case studies that i) individuals have cooperated to publish papers that were eventually retracted in a number of journals, ii) brokers have enabled publication in targeted journals at scale, and iii), within a field of science, not all subfields are equally targeted for scientific fraud. Our results reveal some of the strategies that enable the entities promoting scientific fraud to evade interventions. Our final analysis suggests that this ability to evade interventions is enabling the number of fraudulent publications to grow at a rate far outpacing that of legitimate science."

    #ScientificIntegrity
    #ScientificFraud

    pnas.org/doi/10.1073/pnas.2420

  13. "Science is characterized by collaboration and cooperation, but also by uncertainty, competition, and inequality. While there has always been some concern that these pressures may compel some to defect from the scientific research ethos—i.e., fail to make genuine contributions to the production of knowledge or to the training of an expert workforce—the focus has largely been on the actions of lone individuals. Recently, however, reports of coordinated scientific fraud activities have increased. Some suggest that the ease of communication provided by the internet and open-access publishing have created the conditions for the emergence of entities—paper mills (i.e., sellers of mass-produced low quality and fabricated research), brokers (i.e., conduits between producers and publishers of fraudulent research), predatory journals, who do not conduct any quality controls on submissions—that facilitate systematic scientific fraud. Here, we demonstrate through case studies that i) individuals have cooperated to publish papers that were eventually retracted in a number of journals, ii) brokers have enabled publication in targeted journals at scale, and iii), within a field of science, not all subfields are equally targeted for scientific fraud. Our results reveal some of the strategies that enable the entities promoting scientific fraud to evade interventions. Our final analysis suggests that this ability to evade interventions is enabling the number of fraudulent publications to grow at a rate far outpacing that of legitimate science."

    #ScientificIntegrity
    #ScientificFraud

    pnas.org/doi/10.1073/pnas.2420

  14. "Science is characterized by collaboration and cooperation, but also by uncertainty, competition, and inequality. While there has always been some concern that these pressures may compel some to defect from the scientific research ethos—i.e., fail to make genuine contributions to the production of knowledge or to the training of an expert workforce—the focus has largely been on the actions of lone individuals. Recently, however, reports of coordinated scientific fraud activities have increased. Some suggest that the ease of communication provided by the internet and open-access publishing have created the conditions for the emergence of entities—paper mills (i.e., sellers of mass-produced low quality and fabricated research), brokers (i.e., conduits between producers and publishers of fraudulent research), predatory journals, who do not conduct any quality controls on submissions—that facilitate systematic scientific fraud. Here, we demonstrate through case studies that i) individuals have cooperated to publish papers that were eventually retracted in a number of journals, ii) brokers have enabled publication in targeted journals at scale, and iii), within a field of science, not all subfields are equally targeted for scientific fraud. Our results reveal some of the strategies that enable the entities promoting scientific fraud to evade interventions. Our final analysis suggests that this ability to evade interventions is enabling the number of fraudulent publications to grow at a rate far outpacing that of legitimate science."

    #ScientificIntegrity
    #ScientificFraud

    pnas.org/doi/10.1073/pnas.2420

  15. "Science is characterized by collaboration and cooperation, but also by uncertainty, competition, and inequality. While there has always been some concern that these pressures may compel some to defect from the scientific research ethos—i.e., fail to make genuine contributions to the production of knowledge or to the training of an expert workforce—the focus has largely been on the actions of lone individuals. Recently, however, reports of coordinated scientific fraud activities have increased. Some suggest that the ease of communication provided by the internet and open-access publishing have created the conditions for the emergence of entities—paper mills (i.e., sellers of mass-produced low quality and fabricated research), brokers (i.e., conduits between producers and publishers of fraudulent research), predatory journals, who do not conduct any quality controls on submissions—that facilitate systematic scientific fraud. Here, we demonstrate through case studies that i) individuals have cooperated to publish papers that were eventually retracted in a number of journals, ii) brokers have enabled publication in targeted journals at scale, and iii), within a field of science, not all subfields are equally targeted for scientific fraud. Our results reveal some of the strategies that enable the entities promoting scientific fraud to evade interventions. Our final analysis suggests that this ability to evade interventions is enabling the number of fraudulent publications to grow at a rate far outpacing that of legitimate science."

    #ScientificIntegrity
    #ScientificFraud

    pnas.org/doi/10.1073/pnas.2420

  16. > Docampo, Abalkina, and others say there’s little in the new paper that wasn’t already strongly suspected. But the dramatic confirmation that the study offers may shift the needle, they say. “We’re massively behind the curve on making visible and realizing the extent of the problem,” Kaltenbrunner says. “The sheer scale of it is the takeaway message here.”

    science.org/content/article/sc

    #scientificfraud #publishorperish

  17. > Docampo, Abalkina, and others say there’s little in the new paper that wasn’t already strongly suspected. But the dramatic confirmation that the study offers may shift the needle, they say. “We’re massively behind the curve on making visible and realizing the extent of the problem,” Kaltenbrunner says. “The sheer scale of it is the takeaway message here.”

    science.org/content/article/sc

    #scientificfraud #publishorperish

  18. > Docampo, Abalkina, and others say there’s little in the new paper that wasn’t already strongly suspected. But the dramatic confirmation that the study offers may shift the needle, they say. “We’re massively behind the curve on making visible and realizing the extent of the problem,” Kaltenbrunner says. “The sheer scale of it is the takeaway message here.”

    science.org/content/article/sc

    #scientificfraud #publishorperish

  19. The Francesca Gino case ended with her being found guilty of data manipulation, exposed as a serial plagiarist, and losing her defamation suit against the Data Colada bloggers.

    Here's a very watchable 15-minute summary by Pete Judo: m.youtube.com/watch?si=DW5gVlr

    #ResearchIntegrity #FrancescaGino #ScientificFraud #HarvardUniversity #Plagiarism #DataColada

  20. The Francesca Gino case ended with her being found guilty of data manipulation, exposed as a serial plagiarist, and losing her defamation suit against the Data Colada bloggers.

    Here's a very watchable 15-minute summary by Pete Judo: m.youtube.com/watch?si=DW5gVlr

    #ResearchIntegrity #FrancescaGino #ScientificFraud #HarvardUniversity #Plagiarism #DataColada

  21. The Francesca Gino case ended with her being found guilty of data manipulation, exposed as a serial plagiarist, and losing her defamation suit against the Data Colada bloggers.

    Here's a very watchable 15-minute summary by Pete Judo: m.youtube.com/watch?si=DW5gVlr

    #ResearchIntegrity #FrancescaGino #ScientificFraud #HarvardUniversity #Plagiarism #DataColada

  22. The Francesca Gino case ended with her being found guilty of data manipulation, exposed as a serial plagiarist, and losing her defamation suit against the Data Colada bloggers.

    Here's a very watchable 15-minute summary by Pete Judo: m.youtube.com/watch?si=DW5gVlr

    #ResearchIntegrity #FrancescaGino #ScientificFraud #HarvardUniversity #Plagiarism #DataColada

  23. The Francesca Gino case ended with her being found guilty of data manipulation, exposed as a serial plagiarist, and losing her defamation suit against the Data Colada bloggers.

    Here's a very watchable 15-minute summary by Pete Judo: m.youtube.com/watch?si=DW5gVlr

    #ResearchIntegrity #FrancescaGino #ScientificFraud #HarvardUniversity #Plagiarism #DataColada

  24. #AI #GenerativeAI #ScientificFraud #ChatGPT #ChatBots #AcademicPublishing: "We searched and scraped Google Scholar using the Python library Scholarly (Cholewiak et al., 2023) for papers that included specific phrases known to be common responses from ChatGPT and similar applications with the same underlying model (GPT3.5 or GPT4): “as of my last knowledge update” and/or “I don’t have access to real-time data” (see Appendix A). This facilitated the identification of papers that likely used generative AI to produce text, resulting in 227 retrieved papers. The papers’ bibliographic information was automatically added to a spreadsheet and downloaded into Zotero.

    We employed multiple coding (Barbour, 2001) to classify the papers based on their content. First, we jointly assessed whether the paper was suspected of fraudulent use of ChatGPT (or similar) based on how the text was integrated into the papers and whether the paper was presented as original research output or the AI tool’s role was acknowledged. Second, in analyzing the content of the papers, we continued the multiple coding by classifying the fraudulent papers into four categories identified during an initial round of analysis—health, environment, computing, and others—and then determining which subjects were most affected by this issue (see Table 1). Out of the 227 retrieved papers, 88 papers were written with legitimate and/or declared use of GPTs (i.e., false positives, which were excluded from further analysis), and 139 papers were written with undeclared and/or fraudulent use (i.e., true positives, which were included in further analysis). The multiple coding was conducted jointly by all authors of the present article, who collaboratively coded and cross-checked each other’s interpretation of the data simultaneously in a shared spreadsheet file."

    misinforeview.hks.harvard.edu/