Hybrid Neural-Classical Correction for Frozen Time Series Foundation Models: A Comprehensive Ablation Study on High-Frequency Stock Prediction

Large pretrained time-series models such as TimesFM are attractive for financial forecasting, but raw directional accuracy is a misleading scoreboard in equity markets. An early LoRA adapter in this project appeared to reach roughly 80% directional accuracy; we show this is not evidence of skill. Over a long horizon in a rising market, a trivial "always-up" rule attains comparably high accuracy without using the input at all. To separate genuine skill from this base-rate artifact, we build a reproducible, frozen-data benchmark with expanding walk-forward folds, a stratified held-out-ticker split, honest baselines (zero-shot TimesFM, always-up, random-walk, persistence, AR(1)), and paired significance tests (McNemar, Diebold-Mariano) under Benjamini-Hochberg FDR control. We apply the identical method to two universes -- a tech-heavy NASDAQ-100 and a broad S&P 500 -- reporting excess accuracy over the always-up base rate. Three findings replicate. First, when the historical ~80% condition is recreated, the high number is a base rate of ~0.70 that the fine-tuned model scores below. Second, pooled LoRA shows no directional skill over the base rate at any horizon on either universe (negative at the six-month horizon). Third, per-sector specialization is significantly worse than a single pooled adapter (Diebold-Mariano p<0.001 on held-out stocks at h=128). Fine-tuning's only measurable benefit is a statistically significant reduction in point-forecast error relative to zero-shot TimesFM, which nonetheless does not beat naive baselines and confers no tradeable directional edge. The contribution is methodological: a defensible, fully seeded protocol that prevents the base-rate trap, together with the replicated negative result it produces.

The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form of Large Language Models, future TSFMs may be offered as commercialized, closed-source API services. However, many existing online adaptation methods still rely on white-box access for parameter fine-tuning or gradient backpropagation. This paradigm mismatch raises a question: In black-box online adaptation for TSFMs, what should we learn? We answer this with an insight: the predictive errors of the base model are conditioned on both the input and output of the base model (i.e., the context of errors). To validate this insight, we propose ORCA (Online Residual Contextual Adaptation). We conduct extensive experiments across 5 state-of-the-art TSFMs and 8 datasets to demonstrate the effectiveness of our approach. Furthermore, through ablation studies, we quantitatively analyze the impact of different adapter learning hypotheses on the final adaptation performance in black-box online adaptation. Code available at https://github.com/Fifthky/ORCA.

Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more history into the model improves forecast quality. But in stochastic domains, distant history is often just high-frequency noise, not signal. Hence, the proposed work tests whether this premise actually holds by running continuous context architectures (PatchTST included) through the ETTh1 benchmark. The obtained results contradict the premise: an inverse scaling law shows up clearly, with forecasting error rising as context gets longer. A 3,000-step window causes performance to drop by over 68%, evidence that attention mechanisms are poor at ignoring irrelevant historical volatility. Retrieval-Augmented Forecasting (RAFT) is evaluated as an alternative. RAFT achieves a mean squared error (MSE) of 0.379 with a fixed 720-step window and selective retrieval, outperforming both long-context configurations and zero-shot foundation models (Chronos, Moirai) despite requiring far less computation. In addition, the retrieval step injects only the most relevant historical segments as dynamic exogenous variables, which gives the model a context-informed inductive bias it cannot build on its own from raw sequences. Therefore, foundation models going forward need to shift architecturally toward selective retrieval.