Experiment detail · T-002

Temporal Sequence Memory

A delayed-recall task with temporal structure: information presented early in a sequence must be retained across intervening steps before a decision is required. This probes whether a computational architecture supports useful state retention rather than instantaneous mapping.

01

Results

Chance reference
Bio-constrained
Conventional AI

Range marks show ±1 SD across seeds. All metrics (95% CI, parameter counts, seed counts, training times) are sourced from real NeuroWeave experiment artifacts. Click any row to expand.

Methodological note

The SA-010 decay/leak setting (decay 0.05 / leak 0.02) was selected through exploratory sensitivity analysis on this task. It should be read as a task-specific configuration finding, not as a universal biological conclusion. Confidence intervals are wide relative to the differences between conditions.

02

Specification

A delayed-recall task with temporal structure: information presented early in a sequence must be retained across intervening steps before a decision is required. This probes whether a computational architecture supports useful state retention rather than instantaneous mapping.

The MaleCNS-derived architecture with SA-010 temporal dynamics shows strong performance on this specific delayed-recall task, while the conventional baselines evaluated here do not.

03

Continue