Related papers: Ovopub: Modular data publication with minimal prov…
Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challenging due to the lack of definitive rewards. Current…
Although a standard in natural science, reproducibility has been only episodically applied in experimental computer science. Scientific papers often present a large number of tables, plots and pictures that summarize the obtained results,…
We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its…
Visualisation facilitates the understanding of scientific data both through exploration and explanation of visualised data. Provenance contributes to the understanding of data by containing the contributing factors behind a result. With the…
The web is changing the way in which data warehouses are designed, used, and queried. With the advent of initiatives such as Open Data and Open Government, organizations want to share their multidimensional data cubes and make them…
Literature is the primary expression of scientific knowledge and an important source of research data. However, scientific knowledge expressed in narrative text documents is not inherently machine reusable. To facilitate knowledge reuse,…
Solutions to the classic problems of dealing with heterogeneous data and making entire collections interoperable while ensuring that any annotation, which includes the recognition-and-reward system of scientific publishing, need to fit into…
The Resource Description Framework (RDF) is a semantic network data model that is used to create machine-understandable descriptions of the world and is the basis of the Semantic Web. This article discusses the application of RDF to the…
Distributionally robust optimization is used to tackle decision making problems under uncertainty where the distribution of the uncertain data is ambiguous. Many ambiguity sets have been proposed for continuous uncertainty that build on…
As audio machine learning outcomes are deployed in societally impactful applications, it is important to have a sense of the quality and origins of the data used. Noticing that being explicit about this sense is not trivially rewarded in…
It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch. Thus, robust representation…
Microbiology research has access to a very large amount of public information on the habitats of microorganisms. Many areas of microbiology research uses this information, primarily in biodiversity studies. However the habitat information…
While denoising diffusion and flow matching have driven major advances in generative modeling, their application to tabular data remains limited, despite its ubiquity in real-world applications. To this end, we develop TabbyFlow, a…
Many methods for automated software test generation, including some that explicitly use machine learning (and some that use ML more broadly conceived) derive new tests from existing tests (often referred to as seeds). Often, the seed tests…
As sequencing technologies become more affordable and genomic databases expand continuously, the reuse of publicly available sequencing data emerges as a powerful strategy for studying microbial pathogens. Indeed, raw sequencing reads…
We investigate semiring provenance--a successful framework originally defined in the relational database setting--for description logics. In this context, the ontology axioms are annotated with elements of a commutative semiring and these…
We propose a novel modular debiasing technique applicable to any discrete random source, addressing the fundamental challenge of reliably extracting high-quality randomness from inherently imperfect physical processes. The method involves…
Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support…
Good research data management is essential in modern-day lab work. Various solutions exist that are either highly specific or need a significant effort to be customized appropriately. This paper presents an integrated solution for…
Accurate parsing of citations is necessary for machine-readable scholarly infrastructure. But, despite sustained interest in this problem, existing evaluation techniques are often not generalizable, based on synthetic data, or not publicly…