pith. sign in

Thomas Icard

Identifiers

  • name variant Thomas Icard 0.60 · backfill

Papers (26)

  1. Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds cs.CV · 2026 · author #10
  2. Evaluating Commercial AI Chatbots as News Intermediaries cs.CL · 2026 · author #5
  3. Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction cs.AI · 2026 · author #4
  4. How Causal Abstraction Underpins Computational Explanation cs.LG · 2025 · author #3
  5. Interleaving Logic and Counting math.LO · 2025 · author #2
  6. A Communication-First Account of Explanation cs.MA · 2025 · author #3
  7. Modeling Discrimination with Causal Abstraction cs.CY · 2025 · author #4
  8. Belief in the Machine: Investigating Epistemological Blind Spots of Language Models cs.CL · 2024 · author #5
  9. A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments cs.LG · 2024 · author #5
  10. Probing the Quantitative-Qualitative Divide in Probabilistic Reasoning math.LO · 2023 · author #2
  11. Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions stat.ME · 2023 · author #2
  12. Interpretability at Scale: Identifying Causal Mechanisms in Alpaca cs.CL · 2023 · author #3
  13. Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations cs.AI · 2023 · author #4
  14. Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability cs.AI · 2023 · author #11
  15. Causal Abstraction with Soft Interventions cs.AI · 2022 · author #3
  16. Holistic Evaluation of Language Models cs.CL · 2022 · author #43
  17. Causal Distillation for Language Models cs.CL · 2021 · author #6
  18. Inducing Causal Structure for Interpretable Neural Networks cs.LG · 2021 · author #6
  19. Is Causal Reasoning Harder than Probabilistic Reasoning? cs.LO · 2021 · author #3
  20. On the Opportunities and Risks of Foundation Models cs.LG · 2021 · author #41
  21. A Topological Perspective on Causal Inference cs.AI · 2021 · author #2
  22. Causal Abstractions of Neural Networks cs.AI · 2021 · author #3
  23. Intention as Commitment toward Time cs.LO · 2020 · author #5
  24. Probabilistic Reasoning across the Causal Hierarchy cs.LO · 2020 · author #2
  25. On Open-Universe Causal Reasoning cs.AI · 2019 · author #2
  26. On the Conditional Logic of Simulation Models cs.LO · 2018 · author #2

Mentions

  • 2501.08429 #4 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2508.11214 #3 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2507.05219 #2 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2301.04709 #11 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2410.21195 #5 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2303.02536 #4 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2305.08809 #3 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2401.12631 #5 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2306.14351 #2 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2211.09110 #43 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2307.05659 #2 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2111.13936 #3 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2211.12270 #3 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2112.00826 #6 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2108.07258 #41 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2112.02505 #6 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2107.08558 #2 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2106.02997 #3 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2001.02889 #2 · arxiv_oai · confidence 0.70 Thomas Icard
  • 1907.02170 #2 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2004.08144 #5 · arxiv_oai · confidence 0.70 Thomas Icard
  • 1805.02859 #2 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2505.03732 #3 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2606.25234 #10 · arxiv_oai · confidence 0.70 Thomas Icard
  • 2605.22785 #5 · arxiv_oai · confidence 0.70 Thomas Icard

Frequent Coauthors