Interpretability credit debate points back to Doshi-Velez & Kim's foundational 2017 paper
StephenLCasper · x · 2026-09-07
On X, Stephen Casper was credited for a sequence on interpretability research, but he redirected credit to earlier work—specifically Finale Doshi-Velez and Been Kim's 2017 position paper Towards A Rigorous Science of Interpretable Machine Learning (arXiv:1702.08608).
The paper defines interpretability, discusses when it is (and isn't) needed, and proposes a taxonomy for rigorous evaluation, noting the field still lacks consensus on what interpretability is and how to measure it.
More from Research
- LLM-powered revival of Put-That-There brings speech and gesture window control to XR — twi_mar · 2026-09-07
- Sheet Music to MIDI Pipeline Offers a More Structured Space for Music Models Than Audio — felpix_ · 2026-09-07
- Seen2Scene open-sourced: flow matching trained on real partial scans for 3D scene completion, ECCV 2026 — angelaqdai · 2026-09-07
- Sheet-music generation was already solved in 2019 by Google Magenta's Coconet — felpix_ · 2026-09-07
- Dev open-sources a dependency-free LLM eval harness that catches regressions, not averages — zahidsaim23 · 2026-09-07
- Simulated fruit fly brain gets to "play" Bad Apple in viral demo — SALM0N_SLD · 2026-09-07