BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Steffen Staab

Steffen Staab contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceComputation and Languagecs.CYMachine LearningComputer VisionDatabasesHuman-Computer Interactioncond-mat.stat-mechDistributed, Parallel, and Cluster Computingphysics.soc-phRoboticsSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
0followers
12topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

12 published item(s)

preprint2026arXiv

FutureSim: Replaying World Events to Evaluate Adaptive Agents

AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently measure this capability for realistic use-cases, we propose building grounded simulations that replay real-world events in the order they occurred. We build FutureSim, where agents forecast world events beyond their knowledge cutoff while interacting with a chronological replay of the world: real news articles arriving and questions resolving over the simulated period. We evaluate frontier agents in their native harness, testing their ability to predict world events over a three-month period from January to March 2026. FutureSim reveals a clear separation in their capabilities, with the best agent's accuracy being 25%, and many having worse Brier skill score than making no prediction at all. Through careful ablations, we show how FutureSim offers a realistic setting to study emerging research directions like long-horizon test-time adaptation, search, memory, and reasoning about uncertainty. Overall, we hope our benchmark design paves the way to measure AI progress on open-ended adaptation spanning long time-horizons in the real world.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction

We introduce Graph-Augmented Sequence-to-Sequence (GA-S2S), a novel framework that integrates a T5-small encoder-decoder with a Relational Graph Attention Network (RGAT) to improve link prediction in knowledge graphs. While existing Seq2Seq models rely solely on surface-level textual descriptions of entities and relations and at best, flatten the neighborhoods of a query entity into a single linear sequence, thereby discarding the inherent graph structure, GA-S2S jointly encodes both textual features and the full $k$-hop subgraph topology surrounding the query entity. By integrating raw encoder outputs with RGAT's relation-aware embeddings, our model captures and leverages richer multi-hop relational patterns and textual information. Our preliminary experiments on the CoDEx dataset demonstrate that GA-S2S outperforms competitive Seq2Seq-based baseline models, achieving up to a 19\% relative gain in link prediction accuracy.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks

Relational databases store much of the world's structured information, and they are essential for driving complex predictive applications. However, deep learning progress on relational data remains limited, as conventional approaches flatten databases into single tables via manual feature engineering, discarding relational context. Relational deep learning (RDL) addresses this by modeling databases as relational entity graphs (REGs) for graph neural networks (GNNs), but remains task- and database-specific. To combine the strengths of both paradigms, we propose a hybrid architecture combining a fine-tuned BART encoder to capture intra-row semantics with a GraphSAGE-based GNN over REGs to inject relational context. Experiments on RelBench show that the GNN substantially enriches BART's row embeddings, achieving a ROC-AUC of 67.40 on the driver-dnf task from the rel-f1 dataset. This performance is competitive with supervised baselines such as LightGBM (68.86) and narrows the gap to RDL (72.62) to within 5.22 points, though a substantial gap remains to state-of-the-art foundation models such as KumoRFM (82.63). These results suggest that lightweight hybrid LM-GNN architectures offer a promising and resource-efficient path towards foundation models for relational databases.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge

Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current evaluation practices fall short: existing benchmarks often include questions that can be directly answered using existing triples in KG, making it unclear whether models perform reasoning or simply retrieve answers directly. Moreover, inconsistent evaluation metrics and lenient answer matching criteria further obscure meaningful comparisons. In this work, we introduce a general method for constructing benchmarks and present BRINK (Benchmark for Reasoning under Incomplete Knowledge) to systematically assess KG-RAG methods under knowledge incompleteness. Our empirical results show that current KG-RAG methods have limited reasoning ability under missing knowledge, often rely on internal memorization, and exhibit varying degrees of generalization depending on their design.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Predicting Eye Gaze Location on Websites

World-wide-web, with the website and webpage as the main interface, facilitates the dissemination of important information. Hence it is crucial to optimize them for better user interaction, which is primarily done by analyzing users' behavior, especially users' eye-gaze locations. However, gathering these data is still considered to be labor and time intensive. In this work, we enable the development of automatic eye-gaze estimations given a website screenshots as the input. This is done by the curation of a unified dataset that consists of website screenshots, eye-gaze heatmap and website's layout information in the form of image and text masks. Our pre-processed dataset allows us to propose an effective deep learning-based model that leverages both image and text spatial location, which is combined through attention mechanism for effective eye-gaze prediction. In our experiment, we show the benefit of careful fine-tuning using our unified dataset to improve the accuracy of eye-gaze predictions. We further observe the capability of our model to focus on the targeted areas (images and text) to achieve high accuracy. Finally, the comparison with other alternatives shows the state-of-the-art result of our model establishing the benchmark for the eye-gaze prediction task.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks

Understanding traffic scenes requires considering heterogeneous information about dynamic agents and the static infrastructure. In this work we propose SCENE, a methodology to encode diverse traffic scenes in heterogeneous graphs and to reason about these graphs using a heterogeneous Graph Neural Network encoder and task-specific decoders. The heterogeneous graphs, whose structures are defined by an ontology, consist of different nodes with type-specific node features and different relations with type-specific edge features. In order to exploit all the information given by these graphs, we propose to use cascaded layers of graph convolution. The result is an encoding of the scene. Task-specific decoders can be applied to predict desired attributes of the scene. Extensive evaluation on two diverse binary node classification tasks show the main strength of this methodology: despite being generic, it even manages to outperform task-specific baselines. The further application of our methodology to the task of node classification in various knowledge graphs shows its transferability to other domains.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Formalizing Cost Fairness for Two-Party Exchange Protocols using Game Theory and Applications to Blockchain (Extended Version)

Existing fair exchange protocols usually neglect consideration of cost when assessing their fairness. However, in an environment with non-negligible transaction cost, e.g., public blockchains, high or unexpected transaction cost might be an obstacle for wide-spread adoption of fair exchange protocols in business applications. For example, as of 2021-12-17, the initialization of the FairSwap protocol on the Ethereum blockchain requires the selling party to pay a fee of approx. 349.20 USD per exchange. We address this issue by defining cost fairness, which can be used to assess two-party exchange protocols including implied transaction cost. We show that in an environment with non-negligible transaction cost where one party has to initialize the exchange protocol and the other party can leave the exchange at any time cost fairness cannot be achieved.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ultrahyperbolic Knowledge Graph Embeddings

Recent knowledge graph (KG) embeddings have been advanced by hyperbolic geometry due to its superior capability for representing hierarchies. The topological structures of real-world KGs, however, are rather heterogeneous, i.e., a KG is composed of multiple distinct hierarchies and non-hierarchical graph structures. Therefore, a homogeneous (either Euclidean or hyperbolic) geometry is not sufficient for fairly representing such heterogeneous structures. To capture the topological heterogeneity of KGs, we present an ultrahyperbolic KG embedding (UltraE) in an ultrahyperbolic (or pseudo-Riemannian) manifold that seamlessly interleaves hyperbolic and spherical manifolds. In particular, we model each relation as a pseudo-orthogonal transformation that preserves the pseudo-Riemannian bilinear form. The pseudo-orthogonal transformation is decomposed into various operators (i.e., circular rotations, reflections and hyperbolic rotations), allowing for simultaneously modeling heterogeneous structures as well as complex relational patterns. Experimental results on three standard KGs show that UltraE outperforms previous Euclidean- and hyperbolic-based approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

User Interaction Analysis through Contrasting Websites Experience

Current advance of internet allows rapid dissemination of information, accelerating the progress on wide spectrum of society. This has been done mainly through the use of website interface with inherent unique human interactions. In this regards the usability analysis becomes a central part to improve the human interactions. However, This analysis has not yet quantitatively been evaluated through user perception during interaction, especially when dealing wide range of tasks. In this study, we perform the quantitative analysis the usability of websites based on their usage and relevance. We do this by reporting user interactions based user subjective perceptions, eye-tracking data and facial expressions based on the collected data from two different sets of websites. In general, we found that the user interaction parameters are substantially difference across website sets, with a degree of relation with perceived user emotions during interactions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Bias in Data-driven AI Systems -- An Introductory Survey

AI-based systems are widely employed nowadays to make decisions that have far-reaching impacts on individuals and society. Their decisions might affect everyone, everywhere and anytime, entailing concerns about potential human rights issues. Therefore, it is necessary to move beyond traditional AI algorithms optimized for predictive performance and embed ethical and legal principles in their design, training and deployment to ensure social good while still benefiting from the huge potential of the AI technology. The goal of this survey is to provide a broad multi-disciplinary overview of the area of bias in AI systems, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well-grounded in a legal frame. In this survey, we focus on data-driven AI, as a large part of AI is powered nowadays by (big) data and powerful Machine Learning (ML) algorithms. If otherwise not specified, we use the general term bias to describe problems related to the gathering or processing of data that might result in prejudiced decisions on the bases of demographic features like race, sex, etc.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

GeoSPARQL+: Syntax, Semantics and System for Integrated Querying of Graph, Raster and Vector Data -- Technical Report

We introduce an approach to semantically represent and query raster data in a Semantic Web graph. We extend the GeoSPARQL vocabulary and query language to support raster data as a new type of geospatial data. We define new filter functions and illustrate our approach using several use cases on real-world data sets. Finally, we describe a prototypical implementation and validate the feasibility of our approach.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Time-invariant degree growth in preferential attachment network models

Preferential attachment drives the evolution of many complex networks. Its analytical studies mostly consider the simplest case of a network that grows uniformly in time despite the accelerating growth of many real networks. Motivated by the observation that the average degree growth of nodes is time-invariant in empirical network data, we study the degree dynamics in the relevant class of network models where preferential attachment is combined with heterogeneous node fitness and aging. We propose a novel analytical framework based on the time-invariance of the studied systems and show that it is self-consistent only for two special network growth forms: the uniform and exponential network growth. Conversely, the breaking of such time-invariance explains the winner-takes-all effect in some model settings, revealing the connection between the Bose-Einstein condensation in the Bianconi-Barabási model and similar gelation in superlinear preferential attachment. Aging is necessary to reproduce realistic node degree growth curves and can prevent the winner-takes-all effect under weak conditions. Our results are verified by extensive numerical simulations.

0 citations0 reviewsNo code linkedOpen access