[
    {
        "id": "osp-16472",
        "type": "article-journal",
        "title": "SACQ: Structured Decoding with Memory-Conditioned Refinement for Long-Horizon Forecasting",
        "author": [
            {
                "family": "Cheng",
                "given": "Guo"
            },
            {
                "family": "Xu",
                "given": "Zhengzhuo"
            },
            {
                "family": "Jing",
                "given": "Chenchen"
            },
            {
                "family": "Hou",
                "given": "Jingyi"
            }
        ],
        "URL": "https://omanscience.com/en/articles/sacq-structured-decoding-with-memory-conditioned-refinement-for-long-horizon-forecasting",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Long-term time series forecasting (LTSF) models predominantly employ patch-based encoders terminated by a flatten readout head that maps the entire encoded historical memory to all future steps through a single shared projection. This implicit coupling of future positions obscures position-specific historical-to-future alignment and amplifies sensitivity to corrupted inputs and extreme supervision noise. We present SACQ, a plug-in structured prediction head that replaces flatten readout while keeping the encoder unchanged. SACQ adopts a two-stage decoding pipeline: it first establishes a coarse patch-grid forecast scaffold, then refines each future position through cross-attention over historical memory and merges the attention-derived correction with the coarse scaffold via a learned per-patch gate. To stabilize optimization under long horizons and noisy labels, we further propose a batch-adaptive scaled log-cosh loss that automatically calibrates robustness to the current residual scale, suppressing outlier gradients while preserving MSE-like sensitivity for typical errors. SACQ attains top-tier test MSE/MAE across PatchTST, DLinear, and patch-Mamba backbones with only modest incremental overhead in parameters and latency. Under inference-time input corruption and training-set label-noise stress tests, SACQ substantially outperforms flatten readouts, with ablation studies validating each architectural component."
    }
]