The daily ledger

😺 GPT-6 Sol / Luna vs. Claude Opus 5.5 LIVE

My thoughts on Jev

I‘m sure you heard about Jev, but the information about it you could find was nothing but hype.

Stanford's Paper2Agent Turns Research Papers Into Working AI Agents

Stanford researchers built Paper2Agent, a system that transforms scientific papers from static PDFs into AI agents capable of running analyses, applying methods to new data and collaborating with other research agents.…

Break Your Own RAG Pipeline Before Users Do

A small adversarial test set that catches the retrieval failures your evaluation set never will The post Break Your Own RAG Pipeline Before Users Do appeared first on Towards Data Science.

Build a Speaker-Recognition App with Claude Code

Learn how to effectively code up an internal tool using Claude code or Codex The post Build a Speaker-Recognition App with Claude Code appeared first on Towards Data Science.

OpenClaw 2.0 Is Turning AI Agents Into a Multiplayer Workforce

OpenClaw chief architect Vincent Koc showed how the team is building with dozens of agents, shared sessions, remote compute, model routing, and persistent memory.

4 Ways to Use AI on a PhD Thesis

Finding citations, consolidating code, fact-checking and preparing for the defence The post 4 Ways to Use AI on a PhD Thesis appeared first on Towards Data Science.

An Introduction to Jev

The AI that makes decisions instead of generating text The post An Introduction to Jev appeared first on Towards Data Science.

😺 Amazon blocked Meta’s Muse from shopping

ZoAQ: Adaptive Zeroth-Order Querying via Query-Reuse Coupling

arXiv:2609.22115v1 Announce Type: new Abstract: Zeroth-order optimization (ZOO) estimates updates from function evaluations, making perturbation queries a primary cost. Fixed budgets spend the same number of queries at…

On attention heads and bilinear forms

arXiv:2609.22990v1 Announce Type: new Abstract: We study the symmetric and antisymmetric parts of bilinear forms in the attention heads of trained large language models. We introduce an orthogonally invariant profile…

Can Coding Agents Reproduce Official Statistics? Metadata, Retry Budget and the Limits of Execution Feedback in a Controlled Eurostat Benchmark

arXiv:2609.22222v1 Announce Type: new Abstract: Large language models can generate executable data-analysis code, but successful execution is not equivalent to a valid official-statistics result. This study asks whether…

Rank Portability Does Not Imply Feasibility Portability: Target-Specific Evaluation of Joint Hardware Constraints

arXiv:2609.22122v1 Announce Type: new Abstract: Cross-device hardware evaluation often assumes that if architecture rankings transfer across devices, a proxy device can support target-side model selection. We…

Machine Learning for Invisible Dark Boson Searches at the Electron-Ion Collider

arXiv:2609.22484v1 Announce Type: cross Abstract: We investigate whether adding $t$, the positive magnitude of the squared nuclear four-momentum transfer, enables boosted decision trees (BDTs) to improve…

A Multi-Agent Pipeline for Source-Grounded Synthetic Note Generation from Longitudinal Structured EHR

arXiv:2609.22164v1 Announce Type: cross Abstract: Structured EHR is abundant but sparse, coded, and difficult to use directly for note-centric clinical modeling. We present MedNotes, a multi-agent synthetic data…

A Temporal Knowledge Graph for Music Festival Lineup Forecasting

arXiv:2609.24467v1 Announce Type: new Abstract: Music festival lineups emerge from complex relationships among artists, genres, releases, labels, and past performances, making the prediction of future lineups a natural…

Active Inference as a Convex Markov Decision Process

arXiv:2607.20152v2 Announce Type: replace Abstract: Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single…

Actionable Insights from Observational Data: The Case of Advanced Classes in K-12 Education

arXiv:2609.23836v1 Announce Type: new Abstract: A fundamentally challenging question in K-12 education is about the effects of taking more advanced or challenging classes. It is particularly complex because students…

Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language

arXiv:2608.05238v2 Announce Type: replace Abstract: Training multimodal models to align time series with language runs into a self-supervision trap. The usual recipe asks an LLM to read a series and write a description,…

Q-DEQ: Discrete Solving and Quantization for Deep Equilibrium Models in Time Series Forecasting under Edge Deployment Coding Constraints

arXiv:2609.24042v1 Announce Type: new Abstract: Edge deployment motivates forecasting models with compact parameter storage and low-bit representations. Deep equilibrium models (DEQs) obtain implicit depth by repeatedly…