Peter Carragher

Societal Computing PhD student @S3DatCMU

[IDeaS Center CMU @IDeaSCMU]

📢 2026 Annual IDeaS Conference
📅 Oct 12–14 | 📍Carnegie Mellon Univ. (Hybrid)
Explore misinformation, extremism, & online harms in today’s digital world.
Panels • Talks • Posters • Demos
👉 Register: https://t.co/nWYC3e8Sxz
#SocialCybersecurity #AI #Misinformation

[IDeaS Center CMU @IDeaSCMU]

📢 Our annual Summer Institute training workshop has been rescheduled to August 10–14, 2026. Join us for a week of learning, collaboration, and connection.
Registration is now open!
🔗 https://t.co/SCyWBivycA
We hope you can join us!

[Zhiwei Liu @ZhiweiLiu1008]

📢 Call for Papers: The 2nd Workshop on Misinformation Detection 🔗Details: https://t.co/HBqN6cFLLp
📅 Submission Deadline: March 24

Join us at ICWSM 2026 on May 26, 2026, in Los Angeles, CA!

@icwsm

[ICWSM @icwsm]

📢 Call for Papers: Workshop on Misinformation Detection

We welcome papers focusing on multidisciplinary collaboration in misinformation detection.

📅 Submission Deadline: March 24, 2026
📅Notification: April 15, 2026

🔗Details: https://t.co/G9HuYUlOZv

[Peter Carragher @PeterVCarragher]

Last week, I presented my recent paper on memorization and hallucination in LVLMs at
@l2m2_workshop #ACL2025NLP.

TLDR: model memorization may be more prevalent over image sources vs. text! Details here: https://t.co/kNzT2VtkFd

[Peter Carragher @PeterVCarragher]

Just wrapped up my first IC2S2 conference with a talk on our ongoing research into how broadcasting companies influence editorial decisions in news outlets.

Check out our News Guessing game at https://t.co/IjWIrmBrDR and contribute to our research on media ownership!

[IC2S2 @IC2S2]

That’s a wrap on IC2S2’25! 🎉 Thank you for an unforgettable week of ideas and discussions. Congratulations to our award winners, and safe travels home. Mark your calendars: #ic2s2 ’ 26 heads to Burlington, Vermont, in the US. See you next year!

[Peter Carragher @PeterVCarragher]

SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models (MisD workshop)
https://t.co/ipcu5nD6Pd

[Peter Carragher @PeterVCarragher]

Excited to have two workshop papers and one main conference paper that I've been involved in being presented at @icwsm! Thanks @CatherineKing77 and @ZupEvan for letting me tag along. Details below.

[Peter Carragher @PeterVCarragher]

Mapping the Scientific Literature on Misinformation Interventions: A Bibliometric Review (COMPASS workshop)
https://t.co/jZ3zxa0L7a
@CatherineKing77

[CASOS Center CMU @CMU_CASOS]

Will AI revolutionize Network Science? Come and find out at this year's CASOS and @IDeaSCMU Center's Summer Institute! Registration is still open for the week-long event August 4-8th at Carnegie Mellon University. Find out more at https://t.co/QFgN7qFqos

[Peter Carragher @PeterVCarragher]

Check out the full paper here, which is upcoming at @icwsm MisD workshop (see you in Copenhagen): https://t.co/s5eiyNnYvN

Thanks to my co-authors!
@nikitharao006

[Peter Carragher @PeterVCarragher]

Preprint! Vision-language models like GPT-4o fail to identify multimodal knowledge conflicts and frequently hallucinate on counterfactual samples. Try out the batsman example below (promt = "what is he holding?").

[Peter Carragher @PeterVCarragher]

Finetuning helps identify counterfactual samples and prevent hallucinations.

[Peter Carragher @PeterVCarragher]

And for all the other awesome work building on CommonCrawl, here are the most recently featured papers: https://t.co/ITjW0cE19D

[Peter Carragher @PeterVCarragher]

Our recent paper on source credibility and link spam in Webgraphs got featured on the @CommonCrawl site after being included earlier this year in a special issue on responsible recommender systems in TIST. Check it out here: https://t.co/ip6quhfqMB

@ZupEvan

[Peter Carragher @PeterVCarragher]

We also discussed the possibility of building weighted Webgraphs using the open source tools that CommonCrawl develop. You can checkout the GitHub issue here: https://t.co/kOzuw5E1KN

[CASOS Center CMU @CMU_CASOS]

The 2025 Summer Institute from Aug 4-8 at CMU. The introduction to network science will use AI to generate synthetic network data, label groups & identify missing links in networks. @IDeaSCMU More info: https://t.co/FHBaDgj35a

[CASOS Center CMU @CMU_CASOS]

Center Director Kathleen M. Carley is interviewed by Sophie Perryer for the Logically Facts article entitled, "The 'pink slime' sites sharing sanctioned Russian content with readers in Europe". Read the full article.
https://t.co/w3Izg1PwdD