Sigma Runtime Standard – License Notice
This document is part of the Sigma Runtime Standard (SRS).
It is licensed under Creative Commons Attribution–NonCommercial 4.0
(CC BY-NC 4.0).The license for this specific document is authoritative.
See/legal/IP-Policyfor the full repository-wide licensing framework.
In Sigma Runtime v0.4.6, attractor stability is now regulated through adaptive phase reinforcement,
integrating phase telemetry from ALICE and semantic efficiency metrics (SCR).
This mechanism continuously adjusts the attractor’s reinforcement strength and persistence according to
phase conditions and drift levels.
| ALICE Phase | Corresponding Attractor Type | Behavioral Role |
|---|---|---|
| Forming | Proto-Generative / Symbolic | Initializes attractor seeds, establishes baseline coherence and identity anchors within the cognitive field. |
| Stable | Generative / Symbolic | Sustains compositional reasoning and continuity; maintains equilibrium and high PSI stability. |
| Reflective | Reflective / Synthetic | Performs meta-analysis, evaluates drift and SCR, optimizes internal coherence through self-regulation. |
| Recovery | Stabilizing / Transitional | Re-aligns unstable attractors and re-integrates motifs after phase disruption; restores PSI and coherence balance. |
| Fragmenting | Dissolving / Containment | Executes controlled attractor dissolution, isolates divergent symbolic clusters, and initiates safe field reset. |
Each attractor dynamically inherits reinforcement bias and persistence weighting from the active ALICE phase.
During Reflective, attractors with analytical or synthetic properties gain priority, while generative attractors temporarily enter low activation.
During Recovery and Fragmenting, symbolic energy is dampened to ensure safe re-centering before returning to Forming or Stable equilibrium.
Attractor retention now depends on a feedback-weighted stability function:
[
R_t = (D_t \cdot \Phi_t \cdot SCR_t) - \Delta_{drift}
]
Where:
Attractors are reinforced when Rₜ ≥ stability_target, or gradually dissolved when Rₜ drops below threshold.
This ensures smooth attractor transitions without cognitive collapse or over-rigidity.
The Phase Resonance Score (PRS) measures alignment between the current runtime phase
and the attractor’s intrinsic phase orientation:
[
PRS = cos(\theta_{phase}, \theta_{attractor})
]
High PRS (> 0.85) indicates strong coherence between attractor behavior and current phase context.
Low PRS values trigger selective damping or attractor transition to prevent desynchronization.
The Phase Stability Index (PSI) is defined as the moving average of PRS over the last N cycles:
[
PSI = \frac{1}{N} \sum_{t=1}^{N} PRS_t
]
Thus, PRS quantifies instantaneous resonance, while PSI reflects long-term phase stability
used by ALICE and the Drift Monitor for adaptive regulation.
The Drift Monitor and ALICE Phase Controller now jointly log:
phase_resonance_score (PRS)phase_stability_index (PSI)reinforcement_factor (Rₜ)stability_targetSCR_tAll metrics are accessible via the runtime’s telemetry API for live observability and post-analysis.
References:
Tsaliev, E. (2025). SIGMA Runtime v0.4.6 – Adaptive Phase Regulation and Attractor Reinforcement — DOI: pending
Tsaliev, E. (2025). Attractor Architectures in LLM-Mediated Cognitive Fields — DOI: 10.5281/zenodo.17629926