@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@Techreport{hakken_2026,
  author   = {Tarek R. Besold and Uchenna Akujuobi and Pablo Sanchez and Alessandra Toniato and Kana Maruyama and Jihun Choi and Samy Badreddine and Frederick Gifford and Daniel Evans-Yamamoto and Sucheendra K. Palaniappan and Miquel Ferrer and Kae Nagano and Iris Rossell and Tom Joy and Hatem ElShazly and Chrysa Iliopoulou and Christoph Wehner and Thiviyan Thanapalasingam and Susana Nunes and Pedro G. Cotovio and Peter Wurman and Peter Stone and Hiroaki Kitano and Michael Spranger},
  title    = {Hakken: {P}redicting future discoveries to fill the gaps in today's knowledge},
  institution = "arXiv", 
  number = "arXiv e-Prints 2609.04494",
  year     = {2026},
  abstract = {
              We present Hakken, a domain-agnostic prediction and
              explanation system performing knowledge prediction,
              i.e., growing scientific knowledge by establishing novel
              relationships, ones that are not limited to the
              deductive hull of previous knowledge. Hakken uses a
              transformer-based prediction model built on temporal
              sequences of knowledge graphs extracted from vast bodies
              of research publications, fused with an LLM's semantic
              knowledge, to predict the presence and define the type
              of as-yet undocumented relationships between scientific
              concepts. It then calls a model-agnostic explanation
              framework to provide accompanying information for each
              prediction that allows scientists to evaluate the
              suggested new relationship. While general purpose, we
              demonstrate Hakken's practical capabilities by applying
              it to the biomedical domain. There, Hakken's prediction
              model establishes a new benchmark for time-aware
              multi-label relation prediction, and we show that the
              model's output stays coherent and informative over
              extended time spans in historic data. In addition, we
              scored 1.5 million above-confidence-threshold hypotheses
              related to aging, qualitatively validated batches of
              these predictions with biologists and progressed three
              of them for empirical validation in wet-lab. Two
              predictions with potentially significant impact in the
              context of drug discovery and repurposing were
              confirmed, introducing previously undocumented
              interactions between TP53 and BAMBI, and between RAF1
              and TNF, to biomedical science.
},
  wwwnote={<a href="https://arxiv.org/abs/2609.04494">arXiv version</a>},
}