Cybersickness remains a practical barrier to sustained virtual-reality use because mitigation often begins only after discomfort is reported, while aggressive countermeasures can themselves degrade presence and task performance. This paper presents PAVR, a closed-loop adaptive virtual-reality architecture that reframes mitigation as a constrained control problem: estimate an early-warning cybersickness-risk score from continuously available interaction telemetry, then apply the least disruptive intervention expected to lower that risk. The implemented system uses head angular velocity, head acceleration, translational velocity, controller motion, turning frequency, jerk, task errors, pauses, exposure duration, and frame-performance information to compute a personalized early-warning score. A minimum-cost controller selects among speed reduction, rotation reduction, dynamic field-of-view restriction, motion stabilization, teleportation, or no intervention, while explicitly penalizing presence cost, task cost, and intervention burden. The complete software includes deterministic simulation, three policy baselines, automated tests, a Streamlit research application, one-command reproduction, and continuous integration. In 240 controlled synthetic sessions of 120 steps each, PAVR reduced mean risk from 0.5072 under Fixed VR to 0.3379, eliminated the high-risk fraction observed in the baseline, and used 33.33% less intervention burden than an aggressive threshold-adaptive policy. These results establish software-level computational consistency only; human efficacy remains an empirical question. PAVR therefore provides a reproducible engineering foundation for future real-time, participant-level evaluation of minimally disruptive cybersickness prevention.
Md. Amir Khusru Akhtar· Zenodo (CERN European Organi...· 0 citations
Healthcare artificial intelligence increasingly functions as part of an augmented system in which information, computational resources, external interfaces, and operating rules can alter what a fixed predictive component is able to accomplish. Yet evaluation commonly focuses on final performance, leaving these dependencies largely unexamined. We introduce CARE-X, a non-diagnostic framework for auditing capability in assistive healthcare workflows across the complete 2^4 factorial lattice of resources, information, actions/interfaces, and rules. CARE-X combines exact Boolean-lattice attribution with minimal enabling sets, minimal failure cuts, survival and concentration measures, and workflow-level Capability Passports. We show formally that two augmented systems can exhibit identical technical completion under every intervention while differing in safe capability. Controlled experiments include a 2,048-case simulator and a frozen Random Forest trained on 14,000 synthetic cases. We further examine CARE-X using the open MIMIC-IV-ED Demo, comprising 222 emergency-department stays from 64 patients and 666 non-diagnostic workflow cases. Full augmentation achieves a safe-handling rate of 0.9384. Removing either information or actions/interfaces reduces this rate by 0.6051, with the tied dependency pattern reproduced in a patient-disjoint split. Exact Möbius reconstruction error is zero. In contrast, removal of the rules channel produces a loss of only 0.0015, showing that dependencies observed under controlled conditions need not transfer uniformly to real records. CARE-X thus provides a way to distinguish predictive competence from the operational dependencies that enable safe system capability, while treating the real-record analysis as feasibility evidence rather than clinical validation.
Md. Amir Khusru Akhtar, Arvind Hans· Zenodo (CERN European Organi...· 0 citations
Modern AI capability is increasingly a property of an augmented system rather than a frozen model: test-time computation, retrieved evidence, tools, memory, interfaces, and control rules can all change what is feasible. Generative Calculus II (GC-II) asks where such gains come from. It lifts factorial attribution from scalar scores to task–scale–error–budget capability envelopes and defines an Envelope Attribution Spectrum using Boolean-lattice Möbius inversion. We prove exact attribution, additive-accounting characterization, endpoint non-identifiability, factorial identifiability, and strict refinement of scalar accuracy. We then prove a matched-summary whole-envelope separation: for every fixed projection order, there are balanced envelope families with identical low-order coordinate projections but exact membership-circuit complexities O(n) and Ω(2ⁿ/n), using classical Shannon circuit counting as the lower-bound ingredient. The accompanying public implementation provides reproducible computational results. On handwritten digits, third-order hold-out prediction reduces full-system error from 0.0795 to 0.0162. In a fixed-weight 16-condition FLAN-T5-small pilot comprising 240 evaluations, accuracy rises from 0.20 to 0.60, higher-order interaction mass is 0.4667, and third-order terms predict the held-out full system to machine precision. GC-II therefore separates model capability from system capability while making both attribution and reconstruction complexity auditable.
Md. Amir Khusru Akhtar· Zenodo (CERN European Organi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
