·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings4h◆Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent4h◆From Lookups to Lessons: Turning Retrieved Knowledge into Parametric Memory4h◆Steering Readerly Dynamics: Trajectory-Guided Story Generation with Large Language Models4h◆Spotting the Artificial: Dialogic Humor Improvisation in Humans and LLMs4h◆ElectroChemLLM: A Multimodal LLM Pipeline for High-Fidelity Electrochemical Informatics4h◆Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand4h◆Labadain-MedQA: A Tetun Medical QA Dataset for Fine-Tuning and Evaluating Large Language Models4h◆Reformulation and Equivalence of Bock's Algorithm for Exact Dependency Parsing4h◆Label Smoothing in Disguise? Gated Knowledge Distillation for Low-Resource Bangla Generation4h◆CompSkill: Compiling Execution Experience for Skill Retrieval4h◆GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling4h◆Latent Harness: Compiling Agent Behaviors into Post-Block Activation Shifts4h◆FlyWheel: Attention Kernels Built for the TPU4h◆Towards Fine-grained and Robust Detection of Human-AI Co-authorship4h◆Less but Sufficient: Relation Knowledge Selects Compact Knowledge-Graph Contexts, and What External Checks Can and Cannot Catch4h◆GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation4h◆A Capitulation Direction Emerges With Scale and Is Causally Load-Bearing Where Validation Is Strong: Eight Models, Two Families, and Five Measurement Hazards4h◆Outdated numeric values from Norwegian statutes and regulations in a further-trained model and its base model: a preregistered paired comparison of Borealis 2 and Gemma 44h◆MemShift: Separating Detection from Repair in LLM-Derived Personal Memory4h◆From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings4h◆Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent4h◆From Lookups to Lessons: Turning Retrieved Knowledge into Parametric Memory4h◆Steering Readerly Dynamics: Trajectory-Guided Story Generation with Large Language Models4h◆Spotting the Artificial: Dialogic Humor Improvisation in Humans and LLMs4h◆ElectroChemLLM: A Multimodal LLM Pipeline for High-Fidelity Electrochemical Informatics4h◆Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand4h◆Labadain-MedQA: A Tetun Medical QA Dataset for Fine-Tuning and Evaluating Large Language Models4h◆Reformulation and Equivalence of Bock's Algorithm for Exact Dependency Parsing4h◆Label Smoothing in Disguise? Gated Knowledge Distillation for Low-Resource Bangla Generation4h◆CompSkill: Compiling Execution Experience for Skill Retrieval4h◆GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling4h◆Latent Harness: Compiling Agent Behaviors into Post-Block Activation Shifts4h◆FlyWheel: Attention Kernels Built for the TPU4h◆Towards Fine-grained and Robust Detection of Human-AI Co-authorship4h◆Less but Sufficient: Relation Knowledge Selects Compact Knowledge-Graph Contexts, and What External Checks Can and Cannot Catch4h◆GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation4h◆A Capitulation Direction Emerges With Scale and Is Causally Load-Bearing Where Validation Is Strong: Eight Models, Two Families, and Five Measurement Hazards4h◆Outdated numeric values from Norwegian statutes and regulations in a further-trained model and its base model: a preregistered paired comparison of Borealis 2 and Gemma 44h◆MemShift: Separating Detection from Repair in LLM-Derived Personal Memory4h◆
News/Outdated numeric values from Norwegian statutes and regulations in a further-trained model and its base model: a preregistered paired comparison of Borealis 2 and Gemma 4
arxiv
PublishedNovember 4, 2026 at 5:00 AM

Outdated numeric values from Norwegian statutes and regulations in a further-trained model and its base model: a preregistered paired comparison of Borealis 2 and Gemma 4

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2611.02334v2 Announce Type: new Abstract: We compare how often two released language models give outdated numeric values from Norwegian statutes and regulations: NbAiLab/borealis2-26b-a4b-preview (Borealis 2), which the National Library of Norway further trained from google/gemma-4-26B-A4B-it

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivFrom Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings4harxivFidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent4harxivFrom Lookups to Lessons: Turning Retrieved Knowledge into Parametric Memory4harxivSteering Readerly Dynamics: Trajectory-Guided Story Generation with Large Language Models4h
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews