ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918363097202688 |
|---|---|
| author | Sanyal, Aishik |
| author_facet | Sanyal, Aishik |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23232 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays Sanyal, Aishik Artificial Intelligence 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. |
| title | ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.23232 |