The Morning Preprint

Friday 4 September

Showing the most recent batch — Friday 4 September. No papers have been ingested today yet.

679 papers ingested by the estate's stations that day — about 3 minutes to read. The counts and the chart are the estate's own ingest, not arXiv's submission figures.

This day's harvest looks short: 679 papers against a busiest day of 1650 in the week shown below. Weekends and a broken fetch look the same in the chart, and the chart counts the estate's ingest, not arXiv's.

The 60-second version

Today's batch, and the 60-second version is still being written. Everything below is today's own work: the papers as they are landing, the stations that have written their piece, and the day's episodes. This page fills in as the day does.

The week in the estate's ingest

Seven days of papers the estate ingested. Weekends are striped — the weekend is visible in the data.

643Mon
1650Tue
956Wed
666Thu
679Fri

Show the answer

679 papers were ingested on Friday 4 September.

679 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG137
cs.CL115
cs.AI96
cs.CV48
cs.CR43
astro-ph.GA23
astro-ph.CO22
astro-ph.HE21

The index

The day's strongest 60, by score. Every title links its paper here and on arXiv.

  1. Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories [arXiv] [episode]
  2. Behavior of prediction performance metrics with rare events [arXiv] [episode]
  3. Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation [arXiv] [episode]
  4. Two sets of potential-density basis pairs for the study of radial perturbations in collisionless spherical stellar systems [arXiv] [episode]
  5. Parameterized Hardness of Zonotope Containment and Neural Network Verification [arXiv] [episode]
  6. A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors [arXiv] [episode]
  7. Sealing the Audit-Runtime Gap for LLM Skills [arXiv] [episode]
  8. A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling [arXiv] [episode]
  9. Dark Energy Survey Year 6 Results: Weak Lensing and Galaxy Clustering Cosmological Analysis Framework [arXiv] [episode]
  10. Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models [arXiv] [episode]
  11. From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning [arXiv] [episode]
  12. PalmClaw: A Native On-Device Agent Framework for Mobile Phones [arXiv] [episode]
  13. Linearized subspace refinement framework to expose hidden accuracy in trained neural networks [arXiv] [episode]
  14. Exploring the Impact of Systematic Bias in Type Ia Supernova Cosmology Across Diverse Dark Energy Parametrizations [arXiv] [episode]
  15. MEGATRON: how the first stars can create an iron metallicity plateau in the smallest dwarf galaxies [arXiv] [episode]
  16. ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition [arXiv] [episode]
  17. IDSPACE: A Novel Document Generator for Reliable Evaluation of Digital Identity Verification Systems [Extended Technical Report] [arXiv] [episode]
  18. SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling [arXiv] [episode]
  19. ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models [arXiv] [episode]
  20. EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement [arXiv] [episode]
  21. Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs [arXiv] [episode]
  22. ThreatCore: A Benchmark for Explicit and Implicit Threat Detection [arXiv] [episode]
  23. Metal enrichment in the galaxy group IC 1262 [arXiv] [episode]
  24. Spectral Hierarchy of the Cosmic Web [arXiv] [episode]
  25. NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines [arXiv] [episode]
  26. Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models [arXiv] [episode]
  27. Complete Identification of Deep ReLU Networks through ukasiewicz Logic [arXiv] [episode]
  28. Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment [arXiv] [episode]
  29. Relational Linearity is a Predictor of Hallucinations [arXiv] [episode]
  30. The Atacama Cosmology Telescope: A demonstration of CMB lensing measurement from daytime data [arXiv] [episode]
  31. A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications [arXiv] [episode]
  32. Constraining the origin of magnetic white dwarfs [arXiv] [episode]
  33. Deep Optimizer States: Towards Scalable Training of Transformer Models Using Interleaved Offloading [arXiv] [episode]
  34. XInsight: Revealing Model Insights for GNNs with Flow-based Explanations [arXiv] [episode]
  35. What is Smoothness? [arXiv] [episode]
  36. A Computationally Feasible Framework for Causal Probabilistic Explanation [arXiv] [episode]
  37. Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs [arXiv] [episode]
  38. Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling [arXiv] [episode]
  39. SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling [arXiv] [episode]
  40. PeroMAS: A Multi-agent System of Perovskite Material Discovery [arXiv] [episode]
  41. Temperature Scaling Attack Disrupting Model Confidence in Federated Learning [arXiv] [episode]
  42. Benchmarking Machine Translation on Chinese Social Media Texts [arXiv] [episode]
  43. Evaluating Large Language Models on Urdu Idioms [arXiv] [episode]
  44. Axions as Dark Matter, Dark Energy, and Dark Radiation [arXiv] [episode]
  45. Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring [arXiv] [episode]
  46. Recognition Without Mitigation: Ethical Frameworks in Autonomous Offensive-LLM Agent Research [arXiv] [episode]
  47. A Two-Stage Forecasting System for CPU Workload Prediction in Private Clouds [arXiv] [episode]
  48. Mind the Gap: Robustness Risks in PII Detection Systems [arXiv] [episode]
  49. When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents [arXiv] [episode]
  50. Chehre: An Emoji-Prompted Dataset to Explore Perceptual Flexibility in Video Language Models [arXiv] [episode]
  51. RW-TTT: Batched Serving for Request-Owned Test-Time Training State [arXiv] [episode]
  52. Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning [arXiv] [episode]
  53. Sensitivity of Neutron Star Observables to Transition Density in Hybrid Equation-of-State Models [arXiv] [episode]
  54. Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge [arXiv] [episode]
  55. The Occurrence Rate of Nearby Planetary Companions to Hot Jupiters [arXiv] [episode]
  56. From Leakage to Fidelity: Reliable Benchmarking for Temporal Cascade Prediction [arXiv] [episode]
  57. Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation [arXiv] [episode]
  58. Learning Nonlinear Responses in PET Bottle Buckling with a Hybrid DeepONet-Transolver Framework [arXiv] [episode]
  59. Bubble2Heat: Optical to Thermal Inference in Pool Boiling Using Physics-encoded Generative AI [arXiv] [episode]
  60. Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review [arXiv] [episode]

Listen

Everything the estate published on 2026-09-04, in the player. Playing from this page is how the edition learns whether anyone did.