·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence20m◆The Silent Failures in Agentic Data Science20m◆ClawLoop: Self-Improving Agents via Harness-Native Training Loop20m◆Correction Training for Diffusion Models20m◆Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress20m◆VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary Innovation20m◆Unconstrained CTI-REALM with Open-Weights20m◆Visualizing the World Model in an Agent's Value Function20m◆Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models20m◆Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs20m◆Harness^2: Recursive Agent Harnessing for an Open World20m◆Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference20m◆Controllable Diverse Sampling through Pullback Directions20m◆ConicFlow: constrained Inference-time optimal control for flow matching models20m◆Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions20m◆Actionable Meta-Requirements for AI Robustness Auditing20m◆When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated Healthcare20m◆ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence20m◆ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI20m◆Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware20m◆Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence20m◆The Silent Failures in Agentic Data Science20m◆ClawLoop: Self-Improving Agents via Harness-Native Training Loop20m◆Correction Training for Diffusion Models20m◆Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress20m◆VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary Innovation20m◆Unconstrained CTI-REALM with Open-Weights20m◆Visualizing the World Model in an Agent's Value Function20m◆Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models20m◆Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs20m◆Harness^2: Recursive Agent Harnessing for an Open World20m◆Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference20m◆Controllable Diverse Sampling through Pullback Directions20m◆ConicFlow: constrained Inference-time optimal control for flow matching models20m◆Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions20m◆Actionable Meta-Requirements for AI Robustness Auditing20m◆When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated Healthcare20m◆ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence20m◆ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI20m◆Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware20m◆
News/Signal-Routed Temperature Scaling: Low-Capacity Risk-Conditioned Calibration for Small Validation Budgets
arxiv
PublishedOctober 2, 2026 at 4:00 AM

Signal-Routed Temperature Scaling: Low-Capacity Risk-Conditioned Calibration for Small Validation Budgets

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

arXiv:2609.38936v1 Announce Type: new Abstract: When a classifier is recalibrated from only a few thousand held-out examples, the capacity of the calibration map becomes a statistical design choice rather than a purely architectural one: a scalar map can underfit structured residual miscalibration,

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
arxivArtificiality's First Exam: An LLM-Referenced C-test for Supraintelligence20marxivThe Silent Failures in Agentic Data Science20marxivClawLoop: Self-Improving Agents via Harness-Native Training Loop20marxivCorrection Training for Diffusion Models20m
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