Publications

@article{Serra-2026,
 abstract = {Artificial intelligence (AI) has become central to debates about the future of music, particularly with the rise of generative systems and their societal, economic, cultural, and legal implications. Public and policy discourse, however, often follows commercial narratives that narrow music‑AI to automated generation and treat music primarily as data or commodified output. This obscures both the broader range of AI applications in music and the long‑standing contributions and responsibilities of the music information retrieval (MIR) community. Addressed primarily to this community, the article argues that MIR is well positioned to contribute to current debates on trustworthy music‑AI but must also critically examine the limitations of its own research practices and incentives. We briefly situate MIR’s methodological development, applications, and shared infrastructures, emphasizing the culturally and socially situated character of music data. We then examine ethical, legal, and governance challenges in music‑AI and propose transparency, accountability, provenance, and sustainability as criteria for assessing current practice and guiding future work. Finally, we identify six interconnected priorities: mission‑oriented collaboration; sustainable open infrastructures; rigorous and context‑sensitive evaluation; cultural diversity and responsibility; engagement across research, industry, policy, and society; and interdisciplinary education and mutual capacity‑building. We conclude by identifying ways in which the MIR community can translate these priorities into practice through its research, infrastructures, evaluation and publication processes, educational activities, and engagement with musical, industry, policy, and civil society communities.},
 author = {Serra, Xavier and Alluri, Vinoo and Balke, Stefan and Bello, Juan Pablo and Benetos, Emmanouil and Bogdanov, Dmitry and Devaney, Johanna and Dixon, Simon and Duan, Zhiyao and Fazekas, George and Flexer, Arthur and Font, Frederic and Fuentes, Magdalena and Fujinaga, Ichiro and Gómez, Emilia and Goto, Masataka and Hennequin, Romain and Herremans, Dorien and Hu, Xiao and Jeong, Dasaem and Knees, Peter and Korzeniowski, Filip and Lattner, Stefan and Lee, Jin Ha and Lerch, Alexander and Liem, Cynthia and McFee, Brian and Molina, Emilio and Müller, Meinard and Nakano, Tomoyasu and Nam, Juhan and Nieto, Oriol and Oramas, Sergio and Pardo, Bryan and Peeters, Geoffroy and Rao, Preeti and Richard, Gaël and Rocamora, Martín and Srinivasamurthy, Ajay and Su, Li and Sturm, Bob L. T. and Tzanetakis, George and Volk, Anja and Wang, Ye and Widmer, Gerhard and Wiering, Frans and Weiß, Christof and Yang, Yi-Hsuan and Zangerle, Eva},
 doi = {10.5334/tismir.372},
 journal = {Transactions of the International Society for Music Information Retrieval},
 keyword = {en},
 month = {Sep},
 title = {AI and Music at a Crossroads: The Role of the Music Information Retrieval (MIR) Community in Shaping Trustworthy, Open, and Culturally Inclusive Music‑AI},
 year = {2026}
}

@InProceedings{10.1007/978-3-032-39150-6_33,
author="Bevendorff, Janek
and Fr{\"o}be, Maik
and Greiner-Petter, Andr{\'e}
and Jakoby, Andreas
and Mayerl, Maximilian
and Nakov, Preslav
and Plutz, Henry
and Potthast, Martin
and Stein, Benno
and Ta, Minh Ngoc
and Wang, Yuxia
and Zangerle, Eva",
editor="Hagen, Matthias
and Potthast, Martin
and Stein, Benno
and Schaer, Philipp
and Zangerle, Eva
and MacAvaney, Sean
and Stru{\ss}, Julia Maria
and S{\'a}nchez Salido, Eva
and Barr{\'o}n-Cede{\~{n}}o, Alberto
and Garc{\'i}a Seco de Herrera, Alba",
title="Overview of PAN 2026: Voight-Kampff Generative AI Detection, Text Watermarking, Multi-author Writing Style Analysis, Generative Plagiarism Detection, and Reasoning Trajectory Detection",
booktitle="Experimental IR Meets Multilinguality, Multimodality, and Interaction",
year="2026",
publisher="Springer Nature Switzerland",
address="Cham",
pages="574--597",
abstract="For almost two decades now, the PAN lab has been striving to advance the state of the art in text forensics and stylometry through objective evaluation of new and established methods on curated benchmark datasets. In 2026, we organized five shared tasks: (1) Generative AI detection, particularly in mixed and obfuscated authorship scenarios, (2) Text Watermarking, a new task aiming to evaluate inconspicuousness and robustness of text watermarking techniques, (3) Multi-author Writing Style Analysis, a continued task aiming at identifying authorship position changes, (4) Generative Plagiarism Detection, focusing this year on generated text source retrieval, and (5) Reasoning Trajectory Detection, another new task aiming at source identification and safety assessment of generative reasoning chains. PAN 2026 concluded successfully with more than 200 software submissions and 52 notebook papers.",
isbn="978-3-032-39150-6"
}

@inproceedings{bauer:recsys:2026,
	title        = {Beyond Algorithms: A Workshop on the Interdisciplinarity of Recommender Systems (BEYOND 2026)},
	author       = {Bauer, Christine and Zangerle, Eva and Said, Alan},
	year         = 2026,
	booktitle    = {Proceedings of the 20th ACM Conference on Recommender Systems},
	location     = {},
	publisher    = {Association for Computing Machinery},
	address      = {New York, NY, USA},
	series       = {RecSys '26},
	pages        = {1847–1848},
	doi          = {10.1145/3773078.3831720},
	isbn         = 9798400722844,
	url          = {https://doi.org/10.1145/3773078.3831720},
	abstract     = {Recommendation and personalization research is no longer confined to computer science. Relevant questions are actively explored across disciplines including information systems, communication science, management, cognitive science, psychology, education, media studies, marketing, and the social sciences, often grounded in distinct theories, methods, and evaluation traditions. “Beyond Algorithms: A Workshop on the Interdisciplinarity of Recommender Systems” (BEYOND 2026) aims to create a dedicated space at ACM RecSys 2026 to connect these perspectives.The workshop highlights how insights from adjacent fields can complement, extend, and sometimes challenge computing-centric approaches. It explicitly welcomes contributions studying recommendation, personalization, and related phenomena outside core computing venues, as well as integrative work that bridges computational and non-computational approaches. Through presentations and interactive discussions, we aim to surface diverse theoretical frameworks, methodological traditions, and evaluation paradigms. Our goal is to foster dialogue across disciplinary boundaries, make disciplinary assumptions explicit, and identify shared research challenges and opportunities for collaboration. By strengthening ties between the RecSys community and neighboring research traditions, BEYOND 2026 seeks to broaden participation and visibility for interdisciplinary research and to position RecSys as a hub for both technical innovation and cross-disciplinary exchange.},
	numpages     = 2,
	keywords     = {recommender systems, personalization, interdisciplinarity, cross-disciplinary research, human-centered AI, socio-technical systems, evaluation methodologies, user behavior, societal impact, organizational perspectives}
}

@book{hagen:clef:2026,
 address = {Cham},
 doi = {10.1007/978-3-032-39150-6},
 editor = {Matthias Hagen and
Martin Potthast and
Benno Stein and
Philipp Schaer and
Eva Zangerle and
Sean MacAvaney and
Julia Maria Struß and
Eva Sánchez Salido and
Alberto Barrón-Cedeño and
Alba García Seco de Herrera},
 isbn = {978-3-032-39150-6},
 publisher = {Springer},
 series = {Lecture Notes in Computer Science},
 subtitle = {17th International Conference of the CLEF Association, CLEF 2026,
Jena, Germany, September 21--24, 2026, Proceedings},
 title = {Experimental IR Meets Multilinguality, Multimodality, and Interaction},
 volume = {17087},
 year = {2026}
}

@inproceedings{ijcai2026p926,
  title     = {Beyond Top-1: Addressing Inconsistencies in Evaluating Counterfactual Explanations for Recommender Systems (Extended Abstract)},
  author    = {Mohammadi, Amir Reza and Peintner, Andreas and Müller, Michael M. and Zangerle, Eva},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8278--8283},
  year      = {2026},
  month     = {8},
  note      = {Sister Conferences Best Papers},
  doi       = {10.24963/ijcai.2026/926},
  url       = {https://doi.org/10.24963/ijcai.2026/926},
}

@article{mohammadi:tors:2026,
author = {Mohammadi, Amir Reza and Peintner, Andreas and Mueller, Michael and Zangerle, Eva},
title = {Measuring What Matters: Consistency and Compactness in Evaluation of Counterfactual Explanations},
year = {2026},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3839564},
doi = {10.1145/3839564},
abstract = {Explainability in recommender systems (RS) remains a pivotal challenge. Counterfactual explanations have emerged as a particularly actionable paradigm, offering intuitive “what-if” reasoning. However, their evaluation lacks principled standards. Current metrics primarily assess whether explanations change the top-ranked recommendation, overlooking two fundamental aspects of explanation quality. First, evaluation results are frequently inconsistent, as metrics are tightly coupled to the underlying recommender’s performance. Second, explanations are rarely assessed for compactness—whether changes are sufficiently small to remain interpretable. Oversized counterfactuals may technically succeed but fail to provide practical insight. In this work, we advocate for a holistic evaluation perspective centered on consistency and compactness. We systematically analyze how extending evaluation beyond top-1 to top-k recommendations improves metric stability and reduces dependence on recommender fluctuations. In parallel, we introduce compactness-aware evaluation criteria that quantify the minimality of counterfactual modifications. Through extensive experiments across multiple datasets and models, we demonstrate that jointly considering these dimensions yields more reliable assessments. Our findings expose key factors driving metric instability, highlight the trade-off between effectiveness and explanation size, and provide practical guidelines toward standardized, faithful, and compact evaluation of counterfactual explanations in recommender systems.},
note = {Just Accepted},
journal = {ACM Transactions on Recommender Systems},
month = aug,
keywords = {Recommender Systems, Counterfactual Explanations, Evaluation, Consistency, Compactness}
}

@inproceedings{10.1145/3805712.3809584,
author = {Mohammadi, Amir Reza and Peintner, Andreas and M\"{u}ller, Michael M. and Zangerle, Eva},
title = {Minimal-Perturbation Counterfactuals through Guided Denoising Diffusion for Recommender Systems Explanation},
year = {2026},
isbn = {9798400725999},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3805712.3809584},
doi = {10.1145/3805712.3809584},
abstract = {Counterfactual explanations for recommender systems aim to identify minimal changes to a user's interaction history that would alter the model's recommendation, thereby providing actionable and user-centric explanations. However, existing CE methods often rely on local perturbation or mask-based strategies that require substantial profile modifications and exhibit unstable behavior under fine-grained ranking changes. In this work, we propose DiceRec, a diffusion-based, model-agnostic framework for generating interaction-level counterfactual explanations. DiceRec leverages denoising diffusion probabilistic models to learn the distribution of user interaction histories and integrates counterfactual objectives directly into the reverse diffusion process via guided denoising. By shaping the denoising trajectory at each step, DiceRec generates compact, semantically coherent counterfactuals that induce the desired ranking changes without relying on explicit sparsity regularization or heuristic perturbation budgets. Beyond the method itself, we introduce a fine-grained and constrained evaluation protocol that reveals important differences in explanation quality that are obscured by conventional coarse-grained, percentage-based perturbation schemes. Through extensive experiments, we show that DiceRec consistently outperforms state-of-the-art baselines, particularly in minimal-perturbation scenarios that reflect realistic counterfactual conditions. Our results highlight the advantages of diffusion-based counterfactual generation and underscore the necessity of fine-grained evaluation for faithful explanation assessment in recommender systems.},
booktitle = {Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval},
pages = {1371–1381},
numpages = {11},
keywords = {recommender systems, counterfactual explanation, denoising diffusion probabilistic models, evaluation},
location = {Australia},
series = {SIGIR '26}
}

@inproceedings{10.1145/3774935.3806172,
author = {M\"{u}ller, Michael and Mohammadi, Amir Reza and Peintner, Andreas and Barroso Gstrein, Beatriz and Specht, G\"{u}nther and Zangerle, Eva},
title = {Can Third-Party Annotators Reliably Evaluate Conversational Recommender Systems?},
year = {2026},
isbn = {9798400723117},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3774935.3806172},
doi = {10.1145/3774935.3806172},
abstract = {User-centric evaluation has become a key paradigm for assessing Conversational Recommender Systems (CRS), aiming to capture subjective qualities such as satisfaction, trust, and rapport. To enable scalable evaluation, recent work increasingly relies on third-party annotations of static dialogue logs by crowd workers or large language models. However, the reliability of this practice remains largely unexamined. In this paper, we present a large-scale empirical study investigating the reliability and structure of user-centric CRS evaluation on static dialogue transcripts. We collected 1,053 annotations from 124 crowd workers on 200 ReDial dialogues using the 18-dimensional CRS-Que framework. Using random-effects reliability models and correlation analysis, we quantify the stability of individual dimensions and their interdependencies. Our results show that utilitarian and outcome-oriented dimensions such as accuracy, usefulness, and satisfaction achieve moderate reliability under aggregation, whereas socially grounded constructs such as humanness and rapport are substantially less reliable. Furthermore, many dimensions collapse into a single global quality signal, revealing a strong halo effect in third-party judgments. These findings challenge the validity of single-annotator and LLM-based evaluation protocols and motivate the need for multi-rater aggregation and dimension reduction in offline CRS evaluation.},
booktitle = {Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization},
pages = {351–355},
numpages = {5},
keywords = {Conversational Recommender Systems, User-Centric, Evaluation, User Interaction, Personalization},
location = {
},
series = {UMAP '26}
}

@InProceedings{bevendorff:ecir:2026,
  address =                  {Cham, Switzerland},
  author =                   "Bevendorff, Janek
and Fr{\"o}be, Maik
and Greiner-Petter, Andre
and Jakoby, Andreas
and Mayerl, Maximilian
and Nakov, Preslav
and Plutz, Henry
and Potthast, Martin
and Stein, Benno
and Ta, Minh Ngoc
and Wang, Yuxia
and Zangerle, Eva",
  booktitle =                {Advances in Information Retrieval. 48th European Conference on IR Research (ECIR 2026)},
  doi =                      {10.1007/978-3-032-21321-1_32},
  editor =                   {Ricardo Campos and Adam Jatowt and Yanyan Lan and Mohammad Aliannejadi and Christine Bauer and Sean MacAvaney and Zhaochun Ren and Suzan Verberne and Nan Bai and Masoud Mansoury},
  pages =                    {225--232},
  publisher =                {Springer Nature},
  series =                   {Lecture Notes in Computer Science},
  title =                    {{Overview of PAN 2026: Voight-Kampff Generative AI Detection, Text Watermarking, Multi-author Writing Style Analysis, Generative Plagiarism Detection, and Reasoning Trajectory Detection -- Extended Abstract}},
  volume =                   16485,
  year =                     {2026}
}

@phdthesis{peintner2025dissertation,
  title={{Sequential Recommendation - A Graph-based Perspective}},
  school = {University of Innsbruck, Department of Computer Science},
  author={Andreas Peintner},
  year={2025},
}

@article{mohammadi2025quantitative,
  title={Quantitative Assessment of GNN Counterfactual Explanation Robustness and Reproducibility under Adversarial Influence},
  author={Mohammadi, Amir Reza and M{\"u}ller, Michael M and Peintner, Andreas and Gstrein, Beatriz Barroso and Zangerle, Eva and Specht, G{\"u}nther},
  year={2025},
  booktitle    = {Proceedings of the 36th GI-Workshop Grundlagen von Datenbanken (GvDB 2025), Regensburg, Germany},
}

@article{mohammadi2025quantitative,
  title={Yearning for Better Metrics: Revisiting the ReDial Dataset for Evaluating Conversational Recommender Systems},
  author={M{\"u}ller, Michael M and Mohammadi, Amir Reza and Peintner, Andreas and Gstrein, Beatriz Barroso and Zangerle, Eva and Specht, G{\"u}nther},
  year={2025},
  booktitle={Proceedings of the 36th GI-Workshop Grundlagen von Datenbanken (GvDB 2025), Regensburg, Germany},
}

@inproceedings{zangerle:pan:2025,
  author       = {Eva Zangerle and
                  Maximilian Mayerl and
                  Martin Potthast and
                  Benno Stein},
  title        = {Overview of the Multi-Author Writing Style Analysis Task at {PAN}
                  2025},
  booktitle    = {Working Notes of the Conference and Labs of the Evaluation Forum {(CLEF}
                  2025), Madrid, Spain, 9-12 September, 2025},
  series       = {{CEUR} Workshop Proceedings},
  volume       = {4038},
  pages        = {3568--3574},
  publisher    = {CEUR-WS.org},
  year         = {2025},
  url          = {https://ceur-ws.org/Vol-4038},
}

@InProceedings{bevendorff:2025,
  address =                  {Berlin Heidelberg New York},
  author =                   {Janek Bevendorff and Daryna Dementieva and Maik Fr{\"o}be and Bela Gipp and Andr{\'e} Greiner-Petter and Jussi Karlgren and Maximilian Mayerl and Preslav Nakov and Alexander Panchenko and Martin Potthast and Artem Shelmanov and Efstathios Stamatatos and Benno Stein and Yuxia Wang and Matti Wiegmann and Eva Zangerle},
  booktitle =                {Experimental IR Meets Multilinguality, Multimodality, and Interaction. Proceedings of the Sixteenth International Conference of the CLEF Association (CLEF 2025)},
  editor =                   {Jorge Carrillo-de-Albornoz and Julio Gonzalo and Laura Plaza and Alba Garc{\'i}a Seco Herrera and Josiane Mothe and Florina Piroi and Paolo Rosso and Damiano Spina and Guglielmo Faggioli and Nicola Ferro},
  month =                    9,
  publisher =                {Springer},
  series =                   {Lecture Notes in Computer Science},
  site =                     {Madrid, Spain},
  title =                    {{Overview of PAN 2025: Voight-Kampff Generative AI Detection, Multilingual Text Detoxification, Multi-Author Writing Style Analysis, and Generative Plagiarism Detection}},
  year =                     {2025}
}

@inproceedings{zangerle:recsys:2025,
author = {Zangerle, Eva and Said, Alan and Bauer, Christine},
title = {Beyond Algorithms: Reclaiming the Interdisciplinary Roots of Recommender Systems (BEYOND 2025)},
year = {2025},
isbn = {9798400713644},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3705328.3747998},
doi = {10.1145/3705328.3747998},
abstract = {This workshop challenges the machine learning-centric focus of modern recommender systems research by reconnecting the field with its interdisciplinary origins and exploring the non-algorithmic dimensions that are crucial to effective recommendation. It fosters a space for reflective, critical, and creative discussions on recommender systems that embrace human values, user experiences, and societal impact. The workshop emphasizes methodological diversity and invites contributions from psychology, human-computer interaction, ethics, design, and other disciplines.},
booktitle = {Proceedings of the Nineteenth ACM Conference on Recommender Systems},
pages = {1360–1361},
numpages = {2},
keywords = {recommender systems, interdisciplinary, personalized systems, non-algorithmic dimensions},
location = {
},
series = {RecSys '25}
}

@inproceedings{mohammadi:recsys:2025,
author = {Mohammadi, Amir Reza and Peintner, Andreas and M\"{u}ller, Michael and Zangerle, Eva},
title = {Beyond Top-1: Addressing Inconsistencies in Evaluating Counterfactual Explanations for Recommender Systems},
year = {2025},
isbn = {9798400713644},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3705328.3748028},
doi = {10.1145/3705328.3748028},
abstract = {Explainability in recommender systems (RS) remains a pivotal yet challenging research frontier. Among state-of-the-art techniques, counterfactual explanations stand out for their effectiveness, as they show how small changes to input data can alter recommendations, providing actionable insights that build user trust and enhance transparency. Despite their growing prominence, the evaluation of counterfactual explanations in RS is far from standardized. Specifically, existing metrics show inconsistency since they are affected by variations in the performance of the underlying recommenders. Hence, we critically examine the evaluation of counterfactual explainers through consistency as the key principle of effective evaluation. Through extensive experiments, we assess how going beyond top-1 recommendation and incorporating top-k recommendations impacts the consistency of existing evaluation metrics. Our findings reveal factors that impact the consistency of existing evaluation metrics and offer a step toward effectively mitigating the inconsistency problem in counterfactual explanation evaluation.},
booktitle = {Proceedings of the Nineteenth ACM Conference on Recommender Systems},
pages = {515–520},
numpages = {6},
keywords = {Recommender Systems, Counterfactual Explanation, Evaluation},
location = {
},
series = {RecSys '25}
}

@article{jacobsen:musiscaescientiae:2024,
	title        = {Assessing aesthetic music-evoked emotions in a minute or less: A comparison of the GEMS-45 and the GEMS-9},
	author       = {Peer-Ole Jacobsen and Hannah Strauss and Julia Vigl and Eva Zangerle and Marcel Zentner},
journal = {Musicae Scientiae},
volume = {29},
number = {1},
pages = {184-192},
year = {2025},
doi = {10.1177/10298649241256252},
}

@article{peintner:tismir:2025,
 abstract = {Music emotion recognition (MER) seeks to understand the complex emotional landscapes elicited by music, acknowledging music\’s profound social and psychological roles beyond traditional tasks such as genre classification or content similarity. MER relies heavily on high‑quality emotional annotations, which serve as the foundation for training models to recognize emotions. However, collecting these annotations is both complex and costly, leading to limited availability of large‑scale datasets for MER. Recent efforts in MER for automatically extracting emotion have focused on learning track representations in a supervised manner. However, these approaches mainly use simplified emotion models due to limited datasets or a lack of necessity for sophisticated emotion models and ignore hidden inter‑track relations, which are beneficial in a semi‑supervised learning setting. This paper proposes a novel approach to MER by constructing a multi‑relational graph that encapsulates different facets of music. We leverage graph neural networks to model intricate inter‑track relationships and capture structurally induced representations from user data, such as listening histories, genres, and tags. Our model, the semi‑supervised multi‑relational graph neural network for emotion recognition (SRGNN‑Emo), innovates by combining graph‑based modeling with semi‑supervised learning, using rich user data to extract nuanced emotional profiles from music tracks. Through extensive experimentation, SRGNN‑Emo demonstrates significant improvements in R2 and root mean squared error metrics for predicting the intensity of nine continuous emotions (Geneva Emotional Music Scale), demonstrating its superior capability in capturing and predicting complex emotional expressions in music.},
 author = {Peintner, Andreas and Moscati, Marta and Kinoshita, Yu and Vogl, Richard and Knees, Peter and Schedl, Markus and Strauss, Hannah and Zentner, Marcel and Zangerle, Eva},
 doi = {10.5334/tismir.235},
 journal = {Transactions of the International Society for Music Information Retrieval},
 keyword = {en_US},
 month = {Jun},
 title = {Nuanced Music Emotion Recognition via a Semi-Supervised Multi-Relational Graph Neural Network},
 year = {2025}
}

@article{peintner:tors:2025,
 address = {New York, NY, USA},
 articleno = {46},
 author = {Peintner, Andreas and Mohammadi, Amir Reza and Zangerle, Eva},
 doi = {10.1145/3701764},
 issue_date = {December 2025},
 journal = {ACM Transactions on Recommender Systems},
 keywords = {Recommender systems, session-based recommendation, graph neural network, supervised contrastive learning},
 month = {April},
 number = {4},
 numpages = {24},
 publisher = {Association for Computing Machinery},
 title = {Efficient Session-based Recommendation with Contrastive Graph-based Shortest Path Search},
 url = {https://doi.org/10.1145/3701764},
 volume = {3},
 year = {2025}
}

@inproceedings{peintner2025hyperhawkes,
  author       = {Andreas Peintner and
                  Amir Reza Mohammadi and
                  Michael M{\"{u}}ller and
                  Eva Zangerle},
  title        = {Hypergraph-based Temporal Modelling of Repeated Intent for Sequential
                  Recommendation},
  booktitle    = {Proceedings of the {ACM} on Web Conference 2025, {WWW} 2025, Sydney,
                  NSW, Australia, 28 April 2025- 2 May 2025},
  pages        = {3809--3818},
  publisher    = {{ACM}},
  year         = {2025},
  url          = {https://doi.org/10.1145/3696410.3714896},
  doi          = {10.1145/3696410.3714896}
}

@inproceedings{bevendorff_ecir_2025,
 address = {Cham},
 author = {Bevendorff, Janek
and Dementieva, Daryna
and Fröbe, Maik
and Gipp, Bela
and Greiner-Petter, Andre
and Karlgren, Jussi
and Mayerl, Maximilian
and Nakov, Preslav
and Panchenko, Alexander
and Potthast, Martin
and Shelmanov, Artem
and Stamatatos, Efstathios
and Stein, Benno
and Wang, Yuxia
and Wiegmann, Matti
and Zangerle, Eva},
 booktitle = {Advances in Information Retrieval},
 editor = {Hauff, Claudia
and Macdonald, Craig
and Jannach, Dietmar
and Kazai, Gabriella
and Nardini, Franco Maria
and Pinelli, Fabio
and Silvestri, Fabrizio
and Tonellotto, Nicola},
 isbn = {978-3-031-88720-8},
 pages = {434--441},
 publisher = {Springer Nature Switzerland},
 title = {Overview of PAN 2025: Generative AI Detection, Multilingual Text Detoxification, Multi-author Writing Style Analysis, and Generative Plagiarism Detection},
 year = {2025},
 doi = {10.1007/978-3-031-88720-8_64},
 url = {https://doi.org/10.1007/978-3-031-88720-8_64}
}

@Article{bauer:dagstuhl:2024,
  author =	{Bauer, Christine and Said, Alan and Zangerle, Eva},
  title =	{{Evaluation Perspectives of Recommender Systems: Driving Research and Education (Dagstuhl Seminar 24211)}},
  pages =	{58--172},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2024},
  volume =	{14},
  number =	{5},
  editor =	{Bauer, Christine and Said, Alan and Zangerle, Eva},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.14.5.58},
  URN =		{urn:nbn:de:0030-drops-222655},
  doi =		{10.4230/DagRep.14.5.58},
  annote =	{Keywords: Recommender Systems, Evaluation, Information Retrieval, User Interaction, Intelligent Systems}
}

@inproceedings{10.1145/3640457.3687101,
author = {Said, Alan and Bauer, Christine and Zangerle, Eva},
title = {Reflections on Recommender Systems: Past, Present, and Future (INTROSPECTIVES)},
year = {2024},
isbn = {9798400705052},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3640457.3687101},
doi = {10.1145/3640457.3687101},
abstract = {With the RecSys conference now turning 18 years old, the recommender systems (RS) discipline ventures into adulthood. This workshop serves as a platform for introspection, examining the evolution of RS from its origins in CHI to its current state heavily influenced by and focusing on machine learning. The INTROSPECTIVES workshop aims to foster discussions on the past, present, and future of the RS discipline, inviting the community to reflect on key questions such as the maturation of RS, shifts in research focus, and the impact and success of RS in practice. Topics include the changing landscape of RS problems, the evolving role of RS in addressing choice overload to the current motivations driving RS adoption.},
booktitle = {Proceedings of the 18th ACM Conference on Recommender Systems},
pages = {1237–1238},
numpages = {2},
keywords = {information retrieval, introspection, personalized systems, recommender systems, reflection},
location = {Bari, Italy},
series = {RecSys '24}
}

@InProceedings{10.1007/978-3-031-56072-9_1,
author="Bevendorff, Janek
and Casals, Xavier Bonet
and Chulvi, Berta
and Dementieva, Daryna
and Elnagar, Ashaf
and Freitag, Dayne
and Fr{\"o}be, Maik
and Koren{\v{c}}i{\'{c}}, Damir
and Mayerl, Maximilian
and Mukherjee, Animesh
and Panchenko, Alexander
and Potthast, Martin
and Rangel, Francisco
and Rosso, Paolo
and Smirnova, Alisa
and Stamatatos, Efstathios
and Stein, Benno
and Taul{\'e}, Mariona
and Ustalov, Dmitry
and Wiegmann, Matti
and Zangerle, Eva",
editor="Goharian, Nazli
and Tonellotto, Nicola
and He, Yulan
and Lipani, Aldo
and McDonald, Graham
and Macdonald, Craig
and Ounis, Iadh",
title="Overview of PAN 2024: Multi-author Writing Style Analysis, Multilingual Text Detoxification, Oppositional Thinking Analysis, and Generative AI Authorship Verification",
booktitle="Advances in Information Retrieval",
year="2024",
publisher="Springer Nature Switzerland",
address="Cham",
pages="3--10",
abstract="The paper gives a brief overview of the four shared tasks organized at the PAN 2024 lab on digital text forensics and stylometry to be hosted at CLEF 2024. The goal of the PAN lab is to advance the state-of-the-art in text forensics and stylometry through an objective evaluation of new and established methods on new benchmark datasets. Our four tasks are: (1) multi-author writing style analysis, which we continue from 2023 in a more difficult version, (2) multilingual text detoxification, a new task that aims to translate and re-formulate text in a non-toxic way, (3) oppositional thinking analysis, a new task that aims to discriminate critical thinking from conspiracy narratives and identify their core actors, and (4) generative AI authorship verification, which formulates the detection of AI-generated text as an authorship problem, one of PAN's core tasks. As with the previous editions, PAN invites software submissions as easy-to-reproduce docker containers; more than 400 pieces of software have been submitted from PAN'12 through PAN'23 combined, with all recent evaluations running on the TIRA experimentation platform [8].",
isbn="978-3-031-56072-9"
}

@inproceedings{zangerle:pan:2024,
  author       = {Eva Zangerle and
                  Maximilian Mayerl and
                  Martin Potthast and
                  Benno Stein},
  title        = {Overview of the Multi-Author Writing Style Analysis Task at {PAN}
                  2024},
  booktitle    = {Working Notes of the Conference and Labs of the Evaluation Forum {(CLEF}
                  2024), Grenoble, France, 9-12 September, 2024},
  series       = {{CEUR} Workshop Proceedings},
  volume       = {3740},
  pages        = {2424--2431},
  publisher    = {CEUR-WS.org},
  year         = {2024},
  url          = {https://ceur-ws.org/Vol-3740},
}