cs papers | Gist.Science

Eco-Conscious Master Production Scheduling Under Dual Uncertainty: A Hybrid Approach Using Machine Learning and Stochastic Optimization

This paper proposes a hybrid "predict-and-optimize" framework that integrates LSTM and LightGBM machine learning models with two-stage stochastic optimization to enable eco-conscious, cost-effective production scheduling that dynamically adapts to volatile energy prices and uncertain demand, thereby reducing operational costs and Scope 2 emissions while leveraging negative electricity pricing.

Wiam ALAMI CHENTOUFI, Amine ZITOUNI, Abdellah El BARKANY2026-08-13

💻 computer science

SFTeAST: Integrating Structure, Frequency and Temporal Signals for Temporal Knowledge Graph Completion

The paper proposes SFTeAST, a novel Temporal Knowledge Graph Completion model that integrates structural similarity, spiral complex temporal encoding, and historical frequency filtering to efficiently infer missing facts while enhancing generalization and reducing noise interference in sparse scenarios.

Baohua Qiang, Qingfan Deng, Hong Zheng, Shihao Zhang, Ruidong Chen, Haoran Chen, Shaoni Mao2026-08-13

💻 computer science

An open AI system for dermatology tasks

The paper introduces UniDerm, an open-source dermatology foundation model trained entirely on public data using a novel supervision-denoising contrastive learning approach that achieves specialist-level diagnostic accuracy across diverse skin tones and global benchmarks, offering a reproducible and equitable alternative to proprietary systems.

Hong-Yu Zhou, Linwei Chen, Lijun Liu, Ying Fu, Meng Tian, Zhishou Zhang, Hengfu Cui, Qiang Ju, Qianxi Li, Jungong Han, Y (…)2026-08-13

💻 computer science

Can One Agent Restore Another? Multi-Agent Verification Through Independent Constraint Sources

This study demonstrates that while larger language models can independently recover from conflicting instructions, a smaller coupled agent can restore a perturbed partner's behavior only when the partner's history lacks the conflicting instruction, providing evidence that distributed reliability in multi-agent systems stems from partially independent constraint sources rather than mere generation volume.

Simin Yuan2026-08-13

💻 computer science

From Human Approval to Current Authority: Adaptive Runtime Governance at the Execution Boundary of AI-Enabled Organizational Workflows

This study proposes Adaptive Runtime Governance (ARG) as a framework to address the ethical gap between recorded human approvals and current execution authority in AI workflows, demonstrating through a deterministic prototype that revalidating authorization and policy conditions immediately before execution can technically enforce attributable human authority.

Maria Kollia2026-08-13

💻 computer science

Ethical Field Theory: Computational Foundations and Philosophical Extensions

This paper presents Ethical Field Theory (EFT) as a unified mathematical framework for AI alignment that models ethical regulation as a continuous dynamical system governed by nonlinear field equations, while simultaneously bridging formal computation with six philosophical traditions and establishing seven testable predictions to validate its scientific rigor without conflating mathematical analogy with physical reality.

Ali Moslemi Tabrizi2026-08-13

💻 computer science

Late Delivery Risk Prediction in Supply Chain: Moving from Reactive to Proactive Delay Management

This paper presents a Machine Learning solution for APL Logistics that utilizes a Random Forest classifier trained on historical data and SMOTE technology to predict late delivery risks, enabling the operations team to proactively mitigate delays through a Streamlit dashboard.

Awinash Kumar2026-08-13

💻 computer science

Geometric Indexing Does Not Improve Versioned Memory Retrieval: Three Pre-Registered Negative Results and a Silent Total-Failure Mode

This paper demonstrates through three pre-registered experiments that geometric indexing fails to improve versioned memory retrieval because artificial displacement in embedding space causes unbounded drift away from queries, while coreference resolution remains essential as raw elliptical corrections are unrecoverable and lead to silent total failure.

Maximiliano Rodrigo Speranza2026-08-13

💻 computer science

A Multi-Criteria Decision Framework for Aggregating Ranked ICD-10 Code Suggestions from Large Language Models

This study demonstrates that applying Multi-Criteria Decision Analysis rank aggregation methods, particularly Borda Count and Reciprocal Rank Fusion, to combine outputs from multiple Large Language Models significantly improves the accuracy and stability of automated ICD-10 clinical coding compared to using individual models or simple voting schemes.

Ricardo da Silva Santos, Murilo Gleysson Gazzola, Paulo Marcelino Figueira, Adriana Gomes Luz, Rodolfo de Carvalho Pacag (…)2026-08-13

💻 computer science

Predictive Modeling for Course Demand and Revenue Forecasting on Edupro: Moving from Reactive to Proactive Planning

This paper presents a predictive analytics dashboard for EduPro that resolves faculty-course mismatches and improves revenue forecasting by utilizing a linear regression model, which outperformed Random Forest due to the dataset's small sample size, thereby enabling the company to transition from reactive to proactive planning.

Awinash Kumar2026-08-13

← Previous Next →