Shared Tasks

Important Dates

  • January 31, 2026: Training data released
  • April 23, 2026: Registration closes
  • May 07, 2026: Software submission deadline
  • May 28, 2026: Participant paper submission
  • June 30, 2026: Peer review notification
  • July 06, 2026: Camera-ready participant papers submission
  • September 21-24, 2026: CLEF Conference

The time of all deadlines is Midnight CEST.

Keynotes

Johannes Kiesel
Bringing Computer Science Tools to Social Science: The Methods Hub
GESIS

In computer science in general and at PAN in particular researchers develop tools that can be highly useful for social science research, but social scientists often struggle to apply them to their research questions. While tools may be technically reusable, their documentation rarely explains their different use cases, assumptions, or practical application beyond the original context. Moreover, finding the right tool for a task is a challenge from scientists outside of the original field.

The Methods Hub bridges this gap by making computational methods discoverable, accessible, and practically reusable from a social science perspective. It organizes methods around research use cases and provides practical information, tutorials, and interactive online environments to help social scientists apply them to their own tasks in a reproducible manner.

Johannes Kiesel is head of team BDA at GESIS.

Program (Preliminary)

PAN's program is part of the CLEF 2026 conference program. All times are Central European Summer Time - CEST.

The workshop program will be announced later.
Wednesday, September 23
10:00-10:30Coffee Break and Poster Session
11:15-12:05Lab Overviews (Main Conference)
14:00-15:30Keynote and Lab Session, Chair: TBD, Room: Lecture Room 3.
14:00-14:40Keynote: Bringing Computer Science Tools to Social Science: The Methods Hub
Johannes Kiesel
14:40-15:00Invited Talk: The Impostors Method as a Statistical Test for Authorship Verification With Large Language Models as Sampling Source for Hard Negatives
Klara Gutekunst
15:00-15:30Overview: Reasoning Trajectory Detection
Minh Ngoc Ta, Kaiyang Wan, Yan Lin, Yuxia Wang, Preslav Nakov
15:30-16:00Coffee Break and Poster Session
16:00-17:30Lab Session, Chair: TBD, Room: Lecture Room 3.
16:00-16:30Overview: Plagiarism Detection
André Greiner-Petter, Yun-Ang Wu, Yuka Kitamura, Kon Woo Kim, Maik Fröbe, Bela Gipp, Akiko Aizawa, Martin Potthast
16:30-17:00Overview: Text Watermarking
Henry Plutz, Andreas Jakoby, Janek Bevendorff, Martin Potthast, Benno Stein
17:00-17:15Team JRC-GENESIS at PAN 2026: SYN2 – Hybrid Watermarking via Keyed SYNonym Substitution and SYNtactic Signals
Elisa Di Nuovo, Davide Colla, Quang Luong, Simone Ceppi
17:15-17:30Team aimoment at PAN 2026: Post-Hoc Synonym Watermarking with Dual-Key Type-Level Detection
Momen Fawzy, Nagwa El-Makky, Marwan Torki
Thursday, September 24
11:00-12:30Lab Session, Chair: TBD, Room: Lecture Room 3.
11:00-11:25Overview: Multi-Author Writing Style Analysis
Eva Zangerle, Maximilian Mayerl, Martin Potthast, Benno Stein
11:25-11:35Team SPCRC at PAN 2026: Multi-Encoder Ensemble with Sequential BiLSTM Refinement for Style Change Detection
Shubhankar Kamthankar, Arti Yardi
11:35-11:45Team aimoment at PAN 2026: Content-Agnostic Contrastive Stylometry for Multi-Author Writing Style Analysis
Momen Fawzy, Nagwa El-Makky, Marwan Torki
11:45-11:55Team avocadobeans at PAN 2026: Style Change Detection with DeBERTa, Evidence Aggregation and Sentence Length Embedding
Lukasz Gagala
11:55-12:15Overview: Voight-Kampff Generative AI Detection
Janek Bevendorff, Rohit Raj Gunti, Jussi Karlgren, Maik Fröbe, Martin Potthast, Benno Stein
12:15-12:25Team A&A-detection at PAN 2026: A Hybrid Ensemble of Stylometric, Perplexity, and Neural Features for Voight-Kampff Generative AI Detection
Amalia Voulgaraki, Arina Zamyshevskaya
12:25-12:35Fine-Tuning Fundamentals and Data Augmentation: DS@GT ARC at Voight-Kampff 2026
Harshul Basava, Murilo Gustineli
12:30-14:00Lunch Break
14:00-15:30Lab Session, Chair: TBD, Room: Lecture Room 3.
14:00-14:10Team Suspiciously Coherent at PAN 2026: We stacked two Qwens and hoped for the best
Zuzanna Antoszewska, Natalia Maria Bryła, Alexandra Victoria Szczerba
14:10-14:20Team DACTYL at PAN 2026: Bayesian Data Mixing and Empirical X-risk Minimization for AI-text Detection
Shantanu Thorat
14:20-14:30Team Sinai at PAN 2026: Combining Stylometric Embeddings and IDF Features for Generative AI Text Detection
César Espin-Riofrio, Arturo Montejo-Ráez, Janis Lara-Jama, Jeremy Castro-Illescas
14:30-14:55Overview: Voight-Kampff at ELOQUENT
Rohit Raj Gunti, J M Shalani Dilinika, Devadasu Ghanta, Dima Galat, V A Narayana, Raveendrababu Pakala, Venkateswara Reddy Reddyvari, Marian-Andrei Rizoiu, Juan Manuel Rodriguez, Siva Skandha Sanagala, Antonela Tommasel, Janek Bevendorff, Jussi Karlgren
14:55-15:05Team DArgk at the 2026 ELOQUENT lab for evaluating generative language model quality: Residuals of Humanity: AI Detection Evasion via GRPO Fine-Tuning
Juan Manuel Rodriguez, Antonela Tommasel
15:05-15:30Open Discussion, Closing and Outlook

Participation Modalities

To participate at PAN, first register for your task of choice at CLEF, then follow the instructions below.

Submission

We use TIRA for all submissions to PAN. Please go to tira.io, create an account, and register for the individual tasks you want to participate in. You need to submit your software or your results via TIRA. You can find all submission guides in TIRA's forum.

Data

You can download PAN's datasets here. For details, please check the individual task's website.

Evaluation and Baseline Code

All code used at PAN is published at GitHub. You can find all validators, evaluators, and baselines there.

Software Submissions

PAN promotes reproducible science with software submissions. Please prepare and submit your software as Docker image(s). You can find guides and examples in the resources linked above. Some tasks allow only software submissions and only release the test data after the conference.

Paper Submission and Presentation

PAN is co-located with CLEF 2026 in Jena, Germany. Every participant is expected to write a notebook paper describing their approach to CLEF (published at CEUR-WS, which is indexed by DBLP). At the CLEF conference, all submissions will be presented as talks or posters. CLEF will be a hybrid conference.