pith. sign in

Opening the ai black box: program synthesis via mechanistic interpretability.arXiv preprint arXiv:2402.05110

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

From I/O to Code with Discovery Agent

cs.LG · 2026-05-14 · unverdicted · novelty 7.0

DIO-Agent frames IO2Code as LLM-driven evolutionary search over programs with a Transformation Priority Premise to favor simple hypotheses, outperforming baselines on a new IO2CodeBench.

citing papers explorer

Showing 2 of 2 citing papers.

  • From I/O to Code with Discovery Agent cs.LG · 2026-05-14 · unverdicted · none · ref 15

    DIO-Agent frames IO2Code as LLM-driven evolutionary search over programs with a Transformation Priority Premise to favor simple hypotheses, outperforming baselines on a new IO2CodeBench.

  • Probing for Representation Manifolds in Superposition cs.LG · 2026-05-18 · unverdicted · none · ref 56

    Introduces the Manifold Probe to discover representation manifolds in superposition and demonstrates causal steering on time concepts in Llama 2-7b.