arXiv:2611.18599v1 Announce Type: new
Abstract: Selectively gated state-space models (SSMs), notably Mamba, are increasingly used for financial time series, yet how they internally represent market regimes (bull, bear, sideways) remains opaque. This paper applies Mechanistic Interpretability (MI) to a six-layer Mamba trained on approximately twenty-one years of daily data for a point-in-time set of S&P 500 constituents plus macroeconomic and Fama-French factors, decomposing per-layer hidden states with Top-K Sparse Autoencoders (SAEs). Our central contribution is methodological and cautionary. A prior, uncontrolled configuration recovered market regimes from SAE features at F1 = 1.00. Under a controlled protocol that (i) removes the three input features that overlap the HMM label definition, (ii) disables the auxiliary regime-classification head, (iii) uses a point-in-time constituent universe, and (iv) evaluates against labels disjoint from the inputs, the same regime label is recovered at only F1 = 0.398, indistinguishable from a logistic baseline on raw inputs (0.435) and from an SAE trained on a randomly initialized, untrained Mamba (0.364). A 2×2 attribution grid shows the near-perfect result is an interaction of auxiliary supervision and label-defining inputs: neither factor alone exceeds F1 ~ 0.40. Effect sizes with block-bootstrap inference show the residual selective-gate (Delta t) regime effect is statistically detectable but economically negligible and uniform across layers rather than layer-specialized; the apparent polysemanticity gradient disappears under continuous, theory-grounded measures. We contribute a reproducible leakage-control protocol for interpretability evaluation of financial SSMs, a quantified demonstration that previously reported regime structure is a label-contamination artifact, and a modest economically grounded feature subset that genuinely survives the controls.
Trending
- 11 Types Of Smart Gadgets To Consider Pairing With Your Ring Doorbell
- Don’t Throw Away Your Old Xbox — Do This Instead
- Why data centers are at the center of the Big Tech backlash
- Hebbia sees improvements in financial research with GPT-6 Astra
- You Can Mass-Delete All Of Your Emails On Gmail In Only A Few Clicks
- Perplexity and Intelligence | OpenAI
- 6 Handy Ways You Can Use Your Old Mini PC
- How To Cancel Your Nintendo Switch Online Subscription
