12 papers
Who Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language Agents
Fabio Rovai
Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed action-state graph, and they is…
Independent Verification Paths Are Not Independent: A Case Study of Common-Mode Failure in a Satellite Catalogue Pipeline
Fabio Rovai
A common safeguard for a data pipeline is redundant computation: derive each published number by two routes built on different technology and refuse to exit when they disagree. We…
What an odour descriptor corpus can and cannot measure: valence, attenuation, and the ceiling of the public record
Stylianos Kampakis, Fabio Rovai
Machine olfaction trains on pooled public descriptor corpora, but whether a shared descriptor word measures the same thing across corpora has not been tested, nor has the ceiling o…
Comparability in the public olfactory record: volatile measurement, human perception, and the join between them
Fabio Rovai
Research data infrastructure measures metadata completeness, the share of fields populated. This is the wrong quantity: a populated field is not a joinable field. We measure compar…
Measuring the Installed Base: Nordic Health Dataset Catalogues Against HealthDCAT-AP Release 7
Fabio Rovai
The European Health Data Space requires member states to publish machine readable descriptions of the health datasets available for secondary use, and the European Commission publi…
Consistency Is Not Coherence: Orientation Search for Certified Alignments Between 4D Defence Upper Ontologies
Fabio Rovai
We align three upper ontologies that sit under UK and NATO defence data infrastructure: the Information Exchange Standard (IES), the Higher Quality Data Model (HQDM) that underpins…
Proving the Utility of Large Language Models in Cybersecurity Simulations: A Comprehensive Examination
Stylianos Kampakis, Fabio Rovai, Marcos Charalambides +2
Cyber threats continue to escalate in both frequency and sophistication, necessitating more adaptive and scalable defense strategies. This paper explores how Large Language Models…
WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds
Fabio Rovai
A common assumption holds that enough observational and interventional data, given to a strong enough predictor, suffices. We report a failure mode that contradicts it. Across hund…
Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning
Fabio Rovai
We study event-graph substrates: a class of world models that represent agent state as an append-only log of typed RDF triples and answer counterfactual queries by forking the log…
Saturating Scaling Laws for Equational Discovery: A Phenomenology of Growth Dynamics in Three Toy Substrates with Two Real-World Replications
Fabio Rovai
We investigate growth dynamics in deterministic equational discovery substrates. Across three toy domains (arithmetic, boolean, higher-order list; n=592 trajectories), short-range…
Open Ontologies: Tool-Augmented Ontology Engineering with Stable Matching Alignment
Fabio Rovai
We present Open Ontologies, an open-source ontology engineering system implemented in Rust that integrates LLM-driven construction with formal OWL reasoning and ontology alignment…
CIVeX: Causal Intervention Verification for Language Agents
Fabio Rovai
A valid tool call is not necessarily a valid intervention. Tool-using language agents are guarded by schema validators, policy filters, provenance checks, state predictors, and sel…