The Neurocognitive Threshold Adaptation Map (NTAM) addresses a fundamental question in systems neuroscience: Can two systems that are indistinguishable in the present behave differently because of the histories that produced them? NTAM operationalizes that question through a deterministic computational framework modeli...
Nathaniel Cordova· Zenodo (CERN European Organi...· 0 citations
Replication package for a study of whether large language models preserve the modal force of requirements when extracting them, whether lightweight uncertainty signals expose strengthening of weak stakeholder intent, and whether output-based checks detect it. Contains the frozen prompts, the benchmark, the campaign con...
Nicolas Schuler, Vincenzo Scotti, Raffaela Mirandola· Zenodo (CERN European Organi...· 0 citations
This paper provides the formal mathematical foundation for Boundary 3 of the Instrumentum Vocale verification architecture: the requirement that verification depth must graduate with the falsification degree of the assertion class. It proves that any uniform verification threshold applied to a non-constant falsificatio...
Thorben Liebig· Zenodo (CERN European Organi...· 0 citations
Large Language Models (LLMs) demonstrate strong performance in Natural Language Processing. In neuroanatomy, their response accuracy across hierarchical data structures (responses nested within questions) has not yet been investigated. Evaluating how these models perform under varying cognitive demands is important for...
Büşra Emir, Gonca Ay Keselik· Scientific Reports· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This working paper develops an integrated forecasting model for the transition of human societies from a scarcity system to an abundance system. Its starting point is that solar electricity follows a stable learning curve and is already the cheapest form of power generation. From near-zero-cost energy the paper derives...
Jan Zelenák· Zenodo (CERN European Organi...· 0 citations
Large Language Models (LLMs) are increasingly used for emotion classification, yet Arabic evaluations remain limited and typically emphasise predictive performance alone. This study presents a deployment-oriented evaluation framework for Arabic emotion classification that complements conventional accuracy-based assessm...
Ons Al-Shamaileh, Shaima Alzubi, Mohammed Almehrzi et al.· Scientific Reports· 0 citations
This dataset accompanies the paper "Inferring Gender from Author Names with Local LLMs: A Multi-Model Evaluation" (Journal of Informetrics, 2026). It contains 194,528 first name–country pairs derived from Wikidata, along with gender predictions (Man / Woman / Unknown) produced by 25 open-weight large language models ru...
Anonymous Anonymous· Zenodo (CERN European Organi...· 0 citations
Critical news reading (CNR), which requires grasping the holistic ideas of and raising critical thoughts on the news, is beneficial yet challenging for general people who usually get information on daily social media. Comments under the news can aid CNR by providing complementary information and other readers’ diverse...
Kangyu Yuan, Guanzheng Chen, Sizhe Liang et al.· Proceedings of the ACM on Hu...· 0 citations
Genomes in artificial evolutionary systems have taken many forms, among them bit strings, program instructions, and network weights, none of which makes the expected behavior apparent to a human being. Can a genome state its behavior directly, in ordinary human language, instead? We ask whether a corpus of natural-lang...
Scott Hwang· Zenodo (CERN European Organi...· 0 citations
Data and code for a systematic review of the urban climate literature. A large language model extracted structured information from the full text of every paper, and domain experts checked a sample of that extraction. This package lets you check the data and rebuild the paper's statistics, tables and figures. Start her...
Chenghao Wang, Ting Sun· Zenodo (CERN European Organi...· 0 citations
Organizations use asynchronous AI interview systems to efficiently manage large applicant pools, enabling quick and uniform evaluations. However, concerns remain about their impact on user agency and the lack of personalization applicants experience with these systems. Although efforts have been made to humanize the in...
Md Nazmus Sakib, Naga Manogna Rayasam, Sanorita Dey· Proceedings of the ACM on Hu...· 0 citations
IBF is an open-source toolkit for generating plain-language, impact-based weather forecasts from numerical weather prediction model output. The system integrates ensemble or deterministic model data with large language models to produce consistent, readable forecast narratives, optionally enriched with alert informatio...
Neil D. Gordon· 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
