Literate execution treats documentation and visualizations as dynamic, computable parts of program execution via provenance tracking, inverting traditional literate programming to make programs more explorable.
Towards a Framework for Algorithm Recognition in Binary Code
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Defines a new call-by-silly calculus mirroring call-by-need, proves it shares contextual equivalence with call-by-value, and shows its strategy computes maximal-length sequences via multi types and rewriting.
Hybrid LLM plus static analysis for algorithm recognition in code cuts required model calls by 72-97% and lifts F1-scores by as much as 12 points.
citing papers explorer
-
Literate Execution
Literate execution treats documentation and visualizations as dynamic, computable parts of program execution via provenance tracking, inverting traditional literate programming to make programs more explorable.
-
Mirroring Call-by-Need, or Values Acting Silly
Defines a new call-by-silly calculus mirroring call-by-need, proves it shares contextual equivalence with call-by-value, and shows its strategy computes maximal-length sequences via multi types and rewriting.
-
Combining Static Code Analysis and Large Language Models Improves Correctness and Performance of Algorithm Recognition
Hybrid LLM plus static analysis for algorithm recognition in code cuts required model calls by 72-97% and lifts F1-scores by as much as 12 points.