cs papers | Gist.Science

What Counts as Compute? An Empirical Analysis of Accounting Conventions in Compute-Optimal Transformer Training

This paper demonstrates that while varying accounting conventions for counting parameters and compute significantly alter the fitted exponents of the compute-optimal training frontier, the resulting practical impact on training efficiency is modest due to the flatness of the loss landscape, with the specific accounting choices being predictable from simple architectural ratios.

Alexander Memming2026-07-28

💻 computer science

Bounded-Horizon Local Transformer Training on CPUs: Quality, Throughput, and Memory

This paper evaluates bounded-horizon local training for 24-layer byte-level Transformers on many-core CPUs, finding that while the proposed readout-gradient consensus method achieves a 38% throughput increase over global backpropagation, it fails to meet a 1% non-inferiority criterion for model quality across all tested datasets.

Vikram Lex2026-07-28

💻 computer science

From Forecasting Systems to Agentic Governance: A Structured Critical Review of Computational Models for Political, Economic, and Information Dynamics Structured critical review

This structured critical review reveals that while computational systems have advanced in isolated capabilities like forecasting and simulation, no documented system currently completes a fully validated, adaptive governance loop that empirically demonstrates real-world intervention success under strategic response, highlighting a critical evidence gap between current modular tools and true agentic governance.

Vasiliy Znamenskiy2026-07-28

💻 computer science

Removing Noise or Introducing Bias? The Hidden Cost of MSR Filtering

This study analyzes 1.57 million GitHub repositories to demonstrate that common filtering criteria in Mining Software Repositories (MSR) research introduce significant maintenance, ecosystem, and relational biases that distort project abandonment rates and variable relationships, advocating for a shift toward stratified sampling and refined noise detection.

Mohit Kaushik, Jyoti Bawa2026-07-28✓ Author reviewed ⓘ

💻 computer science

A Search‑Free Foundation Model for Symbolic Regression of Physical Laws

The paper introduces PISR, a search-free foundation model that leverages a physics-informed, contrastively-aligned formula-data manifold and flow matching to rapidly and accurately recover interpretable physical laws from data, outperforming existing methods in both speed and structural accuracy across diverse scientific and real-world benchmarks.

Chenxi He, Jingqiu Chen2026-07-28

💻 computer science

AI Accountability Infrastructure: Cryptographically Verifiable Decision Provenance for High-Stakes AI Systems

This paper proposes the AI Accountability Infrastructure (AAI), a cryptographic framework utilizing hash-chained, digitally signed records and threshold cryptography to enable privacy-preserving, third-party verification of specific AI decision provenance in high-stakes domains, while providing formal models, threat analyses, and regulatory alignments without reporting novel experimental results.

Mezbah Uddin Rafi2026-07-28

💻 computer science

Eco-ITAD: A Real-Time Automated Hardware Diagnostics and Scope 3 ESG Compliance Framework for Sustainable E-Waste Management

This paper proposes Eco-ITAD, a real-time automated system that utilizes Python and Flask to rapidly diagnose hardware conditions and calculate Scope 3 carbon avoidance based on UK DEFRA guidelines, thereby enabling instant, secure, and compliant e-waste management without the need for off-site facilities or local data storage.

Md Saiful Islam, Joyshree Sarkar2026-07-28

💻 computer science

GPT Fusion: Integrating Convolutional Neural Networks with GPT-5.5 for Melanoma Diagnosis

This paper introduces "GPT Fusion," a hybrid diagnostic framework where GPT-5.5 acts as a reasoning engine to integrate predictions from specialized CNN models, significantly outperforming both standalone image-based LLMs and individual CNNs in melanoma diagnosis accuracy and interpretability.

Katie L. Frederickson, Dong Li, Samuel E. Adunyah, Qingguo Wang2026-07-28

💻 computer science

A Heisenberg-Lift Descriptor for Order-Sensitive Online Handwriting Recognition

This paper introduces a lightweight, order-sensitive Heisenberg-lift descriptor, featuring a terminal signed area and a fifteen-dimensional extension, that significantly improves online handwriting recognition accuracy by capturing stroke traversal direction information that traditional Euclidean descriptors miss.

Hassan Ugail, Newton Howard2026-07-28

💻 computer science

Trustworthiness Assessment with Explainable AI: A Comparative Study of LIME, Parzen, and Greedy Explanation Methods on Religious Text and Image Classification

This study evaluates the trustworthiness of LIME, Parzen, and Greedy explanation methods on religious text and image classification models, finding that LIME consistently outperforms the others in identifying untrustworthy features within the specific constraints of the binary text dataset and limited image scope.

Fatima Daws, Sabaa Alansi, Fateen Alharaz, Abdullah Al-Hashedi2026-07-28

← Previous Next →