ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays
Asiem Sanyal
arXiv (Cornell University) February 26, 2026 preprint DOI: 10.48550/arxiv.2602.23232 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Computational modeling study with ablation and lesion experiments |
|---|---|
| Population | Simulated agent (ReCoN-Ipsundrum) in a virtual environment |
| Measures | scenic-entry change, novelty change, scan events, cycle score, tail duration, AUC |
| Key findings | The authors report that affect coupling stabilizes scenic preference against novelty, increases structured scanning, and sustains planned caution, while recurrence supports post-stimulus persistence. They argue these dissociations show that indicator-like signatures can be engineered and that mechanistic and causal evidence should accompany behavioral markers. |
Abstract
Indicator-based approaches to machine consciousness recommend mechanism-linked evidence triangulated across tasks, supported by architectural inspection and causal intervention. Inspired by Humphrey's ipsundrum hypothesis, we implement ReCoN-Ipsundrum, an inspectable agent that extends a ReCoN state machine with a recurrent persistence loop over sensory salience $N^s$ and an optional affect proxy reporting valence/arousal. Across fixed-parameter ablations (ReCoN, Ipsundrum, Ipsundrum+affect), we operationalize Humphrey's qualiaphilia (preference for sensory experience for its own sake) as a familiarity-controlled scenic-over-dull route choice. We find a novelty dissociation: non-affect variants are novelty-sensitive ($Δ$scenic-entry = 0.07). Affect coupling is stable ($Δ$scenic-entry = 0.01) even when scenic is less novel (median {$Δ$novelty $\approx$ -0.43). In reward-free exploratory play, the affect variant shows structured local investigation (scan events 31.4 vs. 0.9; cycle score 7.6). In a pain-tail probe, only the affect variant sustains prolonged planned caution (tail duration 90 vs. 5). Lesioning feedback+integration selectively reduces post-stimulus persistence in ipsundrum variants (AUC drop 27.62, 27.9%) while leaving ReCoN unchanged. These dissociations link recurrence $\rightarrow$ persistence and affect-coupled control $\rightarrow$ preference stability, scanning, and lingering caution, illustrating how indicator-like signatures can be engineered and why mechanistic and causal evidence should accompany behavioral markers.