A cue-locality audit framework for attributing spurious temporal shortcuts in deep sequence models

Abstract High accuracy on independent and identically distributed (IID) test data does not reveal which temporal cue a sequence model uses. A directional process can leave a cue in individual frames, so out-of-distribution (OOD) failure alone does not establish temporal-order use. We propose a six-gate audit that attributes failure to a nuisance and distinguishes frame-local, order-invariant multi-frame, and order-encoded cues. A companion controlled benchmark provides the factor-level probes and interventions the audit requires. Applied to this benchmark, the audit revealed that a variant designed to encode temporal order was instead solvable from individual frames. In the strict order-encoded variant (OE-Strict), direction is readable only from interior frame order. With nuisance direction aligned with the label with probability 0.97 during training, a gated recurrent unit (GRU) trained by empirical risk minimization (ERM) selects the shortcut in thirty of thirty seeds (0.970 IID and 0.030 OOD accuracy). Channel-selective interventions attribute the collapse to nuisance frame ordering. The audit distinguishes which process supports a prediction and whether using that process requires temporal order.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-15
DOI
https://doi.org/10.1038/s41598-026-75482-4
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A cue-locality audit framework for attributing spurious temporal shortcuts in deep sequence models

Dae-Yeol Kim, Do-Yup Kim, Youngjun Kim, YoungJae Cho
Scientific Reports
Explainable Artificial Intelligence (XAI)
article

A cue-locality audit framework for attributing spurious temporal shortcuts in deep sequence models

Dae-Yeol Kim, Do-Yup Kim, Youngjun Kim, YoungJae Cho
article en

Abstract

Abstract High accuracy on independent and identically distributed (IID) test data does not reveal which temporal cue a sequence model uses. A directional process can leave a cue in individual frames, so out-of-distribution (OOD) failure alone does not establish temporal-order use. We propose a six-gate audit that attributes failure to a nuisance and distinguishes frame-local, order-invariant multi-frame, and order-encoded cues. A companion controlled benchmark provides the factor-level probes and interventions the audit requires. Applied to this benchmark, the audit revealed that a variant designed to encode temporal order was instead solvable from individual frames. In the strict order-encoded variant (OE-Strict), direction is readable only from interior frame order. With nuisance direction aligned with the label with probability 0.97 during training, a gated recurrent unit (GRU) trained by empirical risk minimization (ERM) selects the shortcut in thirty of thirty seeds (0.970 IID and 0.030 OOD accuracy). Channel-selective interventions attribute the collapse to nuisance frame ordering. The audit distinguishes which process supports a prediction and whether using that process requires temporal order.

Scientific Reports
Changwon National University (KR), University of Ulsan (KR)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
A cue-locality audit framework for attributing spurious temporal shortcuts in deep sequence models — Dae-Yeol Kim, Do-Yup Kim, et al. · Scientific Reports (2026) | TGRS Research Map | TGRS