·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
The CEO of Allbirds’ new AI biz has a plan, but no employees1h◆A startup claims it broke through a bottleneck that’s holding back LLMs4h◆The US says ASML’s top chip tool may be in China. ASML says it isn’t6h◆Barret Zoph is out at OpenAI again after just five months9h◆Human-AI Agent Interaction in a Business Context10h◆AI4SE and SE4AI Exploration: A Decade Looking Back and Forward10h◆Exit-and-Join Dynamics for Decentralized Coalition Formation10h◆Deontic Policies for Runtime Governance of Agentic AI Systems10h◆Hidden Anchors in Multi-Agent LLM Deliberation10h◆LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data10h◆Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence10h◆Can In-Context Learning Support Intrinsic Curiosity?10h◆PSCT-Net: Geometry-Aware Pediatric Skull CT Reconstruction via Differentiable Back-Projection and Attention-Guided Refinement10h◆One Probe Won't Catch Them All: Towards Targeted Deception Detection10h◆MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning10h◆Granularity-Regulated Adaptive Computational Efficiency for Optimal Verification in Test-Time Scaling10h◆When Does Streaming Tool Use Help? Characterizing Tool-Intent Stabilization in Streaming Retrieval-Augmented Generation10h◆ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion10h◆Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?10h◆Segment-Level Mandarin Chinese Speech-Based Cognitive Impairment Detection via an Autoencoder with Contrastive Learning10h◆The CEO of Allbirds’ new AI biz has a plan, but no employees1h◆A startup claims it broke through a bottleneck that’s holding back LLMs4h◆The US says ASML’s top chip tool may be in China. ASML says it isn’t6h◆Barret Zoph is out at OpenAI again after just five months9h◆Human-AI Agent Interaction in a Business Context10h◆AI4SE and SE4AI Exploration: A Decade Looking Back and Forward10h◆Exit-and-Join Dynamics for Decentralized Coalition Formation10h◆Deontic Policies for Runtime Governance of Agentic AI Systems10h◆Hidden Anchors in Multi-Agent LLM Deliberation10h◆LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data10h◆Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence10h◆Can In-Context Learning Support Intrinsic Curiosity?10h◆PSCT-Net: Geometry-Aware Pediatric Skull CT Reconstruction via Differentiable Back-Projection and Attention-Guided Refinement10h◆One Probe Won't Catch Them All: Towards Targeted Deception Detection10h◆MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning10h◆Granularity-Regulated Adaptive Computational Efficiency for Optimal Verification in Test-Time Scaling10h◆When Does Streaming Tool Use Help? Characterizing Tool-Intent Stabilization in Streaming Retrieval-Augmented Generation10h◆ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion10h◆Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?10h◆Segment-Level Mandarin Chinese Speech-Based Cognitive Impairment Detection via an Autoencoder with Contrastive Learning10h◆
News/DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models
arxiv
PublishedJune 18, 2026 at 4:00 AM
—neutral

DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models

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

arXiv:2606.18557v1 Announce Type: new Abstract: A rule-based logic solver resolves every instance in our benchmark in under 50 microseconds with 100% accuracy; the best frontier language model reaches 65% at best and drops to 23.5% under rendering-robust evaluation (worst case over four surface rend

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

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

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
arxivHuman-AI Agent Interaction in a Business Context10harxivAI4SE and SE4AI Exploration: A Decade Looking Back and Forward10harxivExit-and-Join Dynamics for Decentralized Coalition Formation10harxivDeontic Policies for Runtime Governance of Agentic AI Systems10h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

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

Originally published on arxiv ↗
HomeModelsNews