Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)

[Submitted on 9 May 2026 (v1), last revised 14 Jun 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract:A Mamba state-space model trained only for next-step prediction appears to recover Granger-causal structure through a simple readout $S = |W_{out} W_{in}|$, with early experiments suggesting the phenomenon generalized across architectures and benefited from interventional data at $p < 10^{-5}$. We package the protocol used to test that claim — standardized synthetic generators (VAR/Lorenz/CauseMe-style), three intervention semantics ($do(X=c)$, soft-noise, random-forcing), edge-provenance cards on three real datasets, and size-matched control arms — as a reusable falsification benchmark, and walk the claim through it in five stages. The method-level claim does not survive: (i) a plain linear bottleneck does as well or better; (ii) tuned Lasso beats the bottleneck on synthetic CauseMe-style benchmarks, and on Lorenz-96 (the only real benchmark with unambiguous ground truth) classical PCMCI and Granger lead a tight cluster in which the bottleneck trails; (iii) the headline intervention advantage is roughly 60% a sample-size confound, and the residual disappears under standard $do(X=c)$ interventions, surviving only under a non-standard random-forcing scheme; (iv) even that residual reproduces, with a larger effect, in classical bivariate Granger — the effect is method-agnostic. What survives is a narrow characterization result; the benchmark is the lasting artifact, and each stage above is one of its control arms.

Submission history

From: Aman Chadha Mr. [view email]
[v1] Sat, 9 May 2026 21:12:55 UTC (13 KB)
[v2] Sun, 14 Jun 2026 04:28:47 UTC (13 KB)