nucleation

LIT-1580: Causal scrubbing: results on a paren balance checker

1 min read

Properties6
StatusActive — read 2026-10-27 (NOTE-1195) in full, from the Alignment Forum's own API; worth reading as the worked case of causal scrubbing on a model whose algorithm is known, with the full table of hypotheses, their losses and standard errors, and for the authors' own finding that two more specific hypotheses scored higher for reasons they judge illegitimate (THEORY-1029). Read it knowing that the model and the prior dissection are unpublished, that every number is one run of 2,000 scrubbed samples, and that its prose states the horizon test backwards in two places.
Version2
Tagsrepresentation-learning, causality, anthology-candidate
ExtendsLIT-1549 — Causal Scrubbing: a method for rigorously testing interpretability hypotheses
Cited as “paper” byNOTE-1195 — Chan, Garriga-Alonso, Goldowsky-Dill, Greenblatt, Lin et al. — Causal scrubbing: results on a paren balance checker
Cited as “source” byTHEORY-1029 — On a three-layer parenthesis-balance classifier, causal-scrubbing hypotheses that resample the terms of one head's input separately scored 81% and 84% of the loss recovered against 77% for the less specific hypothesis they refine, and the authors attribute the rise to resampling washing out a signal, not to a better explanation

Graph View

Chan, L., Garriga-Alonso, A., Goldowsky-Dill, N., Greenblatt, R., Lin, T., Nitishinskaya, J., Radhakrishnan, A., Shlegeris, B. & Thomas, N. (2022). Causal scrubbing: results on a paren balance checker. AI Alignment Forum, 3 December 2022.

Read in full on 2026-10-27 (NOTE-1195). One account was drawn from it: THEORY-1029.

Why this is here

The owner asked on 2026-10-27 to “get started on the seven works and markov IBP” that the circuits readings of 2026-10-26 had named without registering. The causal-scrubbing reading (LIT-1549, NOTE-1168) held this post’s results only as the main post’s four-row summary. This is where the method meets a model whose algorithm is known, with standard errors, and where the authors find their own score rewarding a hypothesis for the wrong reason. It bears on THEORY-978 (the count-test result is the authors’ own case of a correlated feature passing), on THEORY-802 and on CLAIM-454.

Backlinks