Information-Theoretic Modeling of the Sustainable Digital Personality Constructs Using Mutual Information Constraints and Reinforcement-Based Utility Balancing
Bibliographic record
Abstract
The paper introduces the probabilistic normalization in combination with the normalization through constraints of mutual information and reinforcement-based utility balancing as an information-theoretic framework to model sustainable digital personality constructs. The first step is to formalize digital personalities using probabilistic graphs, where we use state-space representations with behavioral traits and express the level of personality uncertainty using entropy measures. Markovian dynamics are used to approximate the transition of behavior in stochastic behavior. In order to guarantee long term sustainability, we add mutually information constraints that constrain the divergence between personality states over time, ensuring that they remain stable through KL-divergence thresholds. These limits restrictive to non-stationary surroundings by controlling personality drift. An augmentation of this model by a reinforcement learning formulation, it is the reward function which comes to explicitly penalize information divergence, a trade-off between user utility and stability of information production. Policy optimization is limited with mutual information budgets and mechanisms that dynamically cover the violations are gradient-based. Convergence analysis shows Lyapunov-stable personality paths and provides Pareto-optimality in the tradeoff between utility and constraint. We also determine aensitive phase transitions in the high-entropy limits,inding zones of vulnerability that need adaptive regulators. This principled approach provides a coherent foundation of designing resilient digital agents whose actions can be explained, and is personal and can be limited over time as regards to informational divergence.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".