CertiFOX makes a grounder prove that its low-level CNF output is equivalent to the original high-level first-order logic specification, with an independent checker verifying the proof.
Theory Solving Made Easy with Clingo 5 , booktitle =
5 Pith papers cite this work, alongside 147 external citations. Polarity classification is still indexing.
5
Pith papers citing it
147
external citations · Crossref
representative citing papers
NDProp learns decision heuristics to compute stable models for ASP and shows improved accuracy and scalability in neuro-symbolic benchmarks compared to solver-dependent approaches.
A framework mines spatial, functional, and qualitative commonsense constraints from SGG training data and uses them to correct ranked predictions at inference, yielding consistent gains on three benchmarks.
Formal languages matter as the intermediate representation in neurosymbolic reasoning: first-order logic outperforms logic programming languages (ASP, Pyke) in average accuracy.
Using CSR sparse matrix storage speeds up linear algebraic logic programming, making least-model computation practical for programs with hundreds of thousands of rules.
citing papers explorer
-
Towards a Certifying Grounder
CertiFOX makes a grounder prove that its low-level CNF output is equivalent to the original high-level first-order logic specification, with an independent checker verifying the proof.
-
Neural Decision-Propagation for Answer Set Programming
NDProp learns decision heuristics to compute stable models for ASP and shows improved accuracy and scalability in neuro-symbolic benchmarks compared to solver-dependent approaches.
-
Visual Commonsense Driven Knowledge Refinements for Scene Graph Generation
A framework mines spatial, functional, and qualitative commonsense constraints from SGG training data and uses them to correct ranked predictions at inference, yielding consistent gains on three benchmarks.
-
Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning
Formal languages matter as the intermediate representation in neurosymbolic reasoning: first-order logic outperforms logic programming languages (ASP, Pyke) in average accuracy.
-
Enhancing Linear Algebraic Computation of Logic Programs Using Sparse Representation
Using CSR sparse matrix storage speeds up linear algebraic logic programming, making least-model computation practical for programs with hundreds of thousands of rules.