One-minute-ahead direct forecasting performs similarly to contemporaneous estimation, but performance degrades at longer horizons and a carry-forward baseline outperforms the sensor model at every future horizon¶
Claim · All claims
Evidence · 1 study · associationalr1·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Class MAE changes only from 0.753 at t+0 to 0.756 at t+1, but the carry-forward baseline outperforms the directly trained sensor model at every future horizon, demonstrating substantial temporal persistence in the self-reported ratings. → Zikang Leng 2026
Evidence¶
Zikang Leng 2026¶
Zikang Leng, Edan Eyal, Yingtian Shi, Jiaman He, Yaqi Liu, and Thomas Plötz. (2026). EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning. Proc. ACM Interact. Mob. Wearable Ubiquitous Ubiquitous Technol. https://arxiv.org/abs/2605.01238 doi:10.48550/arxiv.2605.01238
q2 · i? · associational · r1
Temporal predictability analysis (Table 7) comparing contemporaneous estimation and direct forecasting at approximately one- to three-minute horizons against carry-forward baselines, evaluated on identical data across horizons under participant-grouped folds. Relative to t+1, Within-1 accuracy decreased by 4.13 and 8.23 percentage points at t+2 and t+3.
"The carry-forward baseline outperforms the directly trained sensor model at every future horizon, demonstrating substantial temporal persistence in the self-reported ratings."
Discussion¶
Related Claims¶
- A modality-aware reference model outperforms sensor-free, statistical, deep temporal, foundation-model, and LLM-based baselines for estimating minute-level attention difficulty from wearable sensing — related
- Chest-worn ECG provides the strongest cardiac-sensing performance for attention-difficulty prediction, and fusing all cardiac streams does not improve upon chest ECG alone — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
engagement-forecasting-horizon-degradation |
title |
One-minute-ahead direct forecasting performs similarly to contemporaneous estimation, but performance degrades at longer horizons and a carry-forward baseline outperforms the sensor model at every future horizon |
description |
One-minute-ahead direct forecasting performs similarly to contemporaneous estimation, but performance degrades at longer horizons and a carry-forward baseline outperforms the sensor model at every future horizon |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — zikang-leng-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.