This paper develops a unified framework — the predictive horizon framework — across three domains: the phenomenology of temporal experience, the failure dynamics of large language models, and the automated detection of scientific novelty. The unifying principle is the lag-adequacy condition: a system's representation o...
Michael Warrington, Claude.ai chatgpt· Zenodo (CERN European Organi...· 0 citations
How Context Shapes LLM-Based and Agentic Detection of Design and Architecture Smells Abstract Design and architecture smells degrade software maintainability, yet detecting them with Large Language Models (LLMs) remains challenging because relevant context spans multiple components. This replication package supports a...
Anonymous· Zenodo (CERN European Organi...· 0 citations
AI Database Optimizer analyses and optimizes SQL queries for MySQL and PostgreSQL. Recommendations of large language models (GigaChat, YandexGPT, OpenAI-compatible, local models via Ollama) are accepted only after safety, schema, result-equivalence and benchmark checks. The release includes SQL Optimization Dataset v1....
Artyom Yakovlev· Zenodo (CERN European Organi...· 0 citations
AI Database Optimizer analyses and optimizes SQL queries for MySQL and PostgreSQL. Recommendations of large language models (GigaChat, YandexGPT, OpenAI-compatible, local models via Ollama) are accepted only after safety, schema, result-equivalence and benchmark checks. The release includes SQL Optimization Dataset v1....
Artyom Yakovlev· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A curated collection of 62 foundational papers on Embodied AI, Vision-Language-Action (VLA) models, Sim2Real transfer, and the integration of Large Language Models with ROS 2. Includes structured metadata (papers.csv), research protocol, and identified research gaps across four sublines: multimodal perception, semantic...
Henry Antonio Roncancio Velandia· Zenodo (CERN European Organi...· 0 citations
The automated categorization of Arabic text remains a persistently difficult problem, largely because the language combines a productive root-and-pattern morphology, pervasive orthographic variation, and a scarcity of large, carefully annotated corpora—factors that together inflate the feature space and obscure the sig...
Hosam Ali AlZawam, Tarik Milod Alarbi Ahmad· Al-Farooq Journal of Science...· 0 citations
A curated collection of 62 foundational papers on Embodied AI, Vision-Language-Action (VLA) models, Sim2Real transfer, and the integration of Large Language Models with ROS 2. Includes structured metadata (papers.csv), research protocol, and identified research gaps across four sublines: multimodal perception, semantic...
Henry Antonio Roncancio Velandia· Zenodo (CERN European Organi...· 0 citations
The Universal Algorithm Physics Walls, Collective Solutions, and the Architecture of Complexity The Universal Algorithm is the general-audience synthesis of a developing research programme at the intersection of complexity science, evolutionary theory and artificial life. The programme investigates recurring patterns i...
Jason Prevett· Zenodo (CERN European Organi...· 0 citations
Version 3 (2026-09-26) corrects a citation error in versions 1 and 2 and a false correction added in version 2, found by an independent audit and confirmed by re-checking every cited arXiv abstract. The inference-system fingerprinting findings, one of the four topics named in the title, were cited to arXiv:2605.29960;...
Saluca Agentic AI Research Team· Zenodo (CERN European Organi...· 0 citations
We investigate bias in academic mental health as reflected by Large Language Models (LLMs). To this aim, we introduce PhDGPT, a synthetic dataset encapsulating the machine psychology of Ph.D. researchers and professors as perceived by OpenAI’s GPT-3.5 and GPT-OSS-20b. The dataset consists of 18,000 data points for each...
Edoardo Sebastiano De Duro, Enrique Taietta, Simon D’Alfonso et al.· Information Processing & Man...· 0 citations
Cultural personas have emerged as a promising technique for enhancing creativity in Large Language Models, yet their effectiveness across different architectures, domains, and economic contexts remains poorly understood. This study provides a systematic evaluation of three cultural personas—Culture\_5 (innovator), Cult...
Youssef Hariri· Zenodo (CERN European Organi...· 0 citations
Vision-language foundation models (VLMs) have demonstrated broad competence across medical imaging tasks, raising the question of whether they can match purpose-built, specialised AI systems for high-stakes 3D CT screening tasks. This talk presents a retrospective benchmark comparing eight VLM configurations — MedGemma...
Pierre Baudot, Benjamin Renoust, Jean‐Christophe Brisset et al.· Zenodo (CERN European Organi...· 0 citations
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
