Predicting how many tokens a large language model (LLM) will decode, using only prefill-phase hidden states, is a key primitive for inference scheduling. We show that current benchmarks conflate predictor quality with task hardness: when the target model, dataset, or sampling configuration changes, reported accuracy collapses even though the predictor is unchanged. We trace this instability to an overlooked error source---the inherent stochasticity of autoregressive decoding---and derive bounds that every prefill-side method must obey. Our analysis treats decoding as a stopped stochastic process. The per-step stopping probability of a response is not constant but ramps up over hundreds of steps, so the decode length inherits a central limit theorem from the many local decisions that determine where a response ends; this yields per-prompt normality with an explicit error term, together with an affine variance law $σ=αμ+b$ whose slope is the coefficient of variation of the number of response segments. Empirically, the normal law reproduces the per-prompt MAE and the central mass of the decode-length distribution to within a few percent, and the residual departures from normality (mild right skew, slight excess kurtosis) are the ones predicted by the sampling-noise correction. Under fixed model, data, and sampling conditions, a broad design space of predictors (MLP, EGTP, FiLM, soft-label, and Mixture-of-Experts variants) converges to similar performance close to the bound, confirming that \emph{system error dominates model error}. We argue for a benchmarking protocol that fixes the model, data, and sampling parameters and that reports relative-error metrics alongside absolute ones. Code and analysis tools are available at https://github.com/ShwStone/DecodingPredict.
Continuous glucose monitoring (CGM) provides a dense view of daily metabolic physiology, yet existing generic time-series and CGM-specific foundation models often encode glucose traces as entangled single-stream sequences, leaving their multiscale temporal structure only implicitly modeled. We present GlucoFM, a lightweight CGM foundation model that aligns irregular recordings to a 24-hour chronological grid, preserves observation masks, and decomposes glucose dynamics into slow-varying glycemic trend and short-term deviation streams. GlucoFM is pretrained on 109,066 hours of unlabeled CGM recordings from 477 subjects with masked contextual latent prediction over fused daily representations and temporal dynamics prediction over the two streams. Frozen pre-fusion probes confirm distinct temporal emphasis: state tokens preferentially preserve hourly glucose level, whereas event tokens better retain short-term change. Across four diverse cohorts and seven phenotype-classification tasks, GlucoFM achieves the strongest subject-disjoint linear-probing performance among evaluated baselines, improving average PR-AUC by 4.1 points over the best CGM-specific foundation model, while also supporting strong cross-dataset transfer and few-shot adaptation. Its gains are most pronounced on core metabolic outcomes, leading PR-AUC on all diabetes-risk and $β$-cell dysfunction tasks and on 3 of 4 insulin-resistance tasks. Beyond phenotyping, when combined with recent CGM, meal nutrition, and subject context, the same frozen encoder achieves the lowest two-hour postprandial glycemic response errors among evaluated methods for trajectory, incremental area under the curve, peak rise, and peak timing. Together, these results demonstrate that GlucoFM learns reusable frozen CGM representations spanning metabolic phenotyping and context-conditioned glucose-response prediction.
Wearable devices generate continuous physiological and behavioral data, but converting these signals into clinically reviewable biomarker hypotheses remains labor-intensive. We introduce CoDaS, an AI co-data-scientist that integrates multi-agent hypothesis generation, deterministic statistical analysis, adversarial validation and literature-grounded interpretation under human oversight. Across three wearable cohorts comprising 9,279 participant-observations, CoDaS prioritized candidate associations for mental-health and metabolic endpoints after internal checks for replication, stability, robustness and leakage. The system identified related circadian-instability signals associated with depression, including sleep-duration variability in DWB ($ρ$ = 0.252, $p$ < 0.001) and sleep-onset variability in GLOBEM ($ρ$ = 0.126, $p$ < 0.001), and derived a wearable cardiovascular-fitness index associated with insulin resistance (steps/resting heart rate; $ρ$ = -0.374, $p$ < 0.001). Adding these features to demographic models produced modest gains ($ΔR^2$ = 0.040 for depression, 0.021 for insulin resistance). In a 12-clinician review totaling approximately 25 active hours, clinician validity judgments aligned with CoDaS confidence tiers ($ρ$ = 0.67, $p$ = 0.005), whereas added clinical value and confidence to act were rated lower. CoDaS supports traceable, hypothesis-generating prioritization of wearable candidate biomarkers.