The Morning Preprint

Thursday 20 August

Showing the most recent batch — Thursday 20 August. No papers have been ingested today yet.

186 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: 186 papers against a busiest day of 475 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.

406Fri
475Mon
432Tue
52Wed
186Thu

Show the answer

186 papers were ingested on Thursday 20 August.

186 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG33
cs.CL29
cs.AI22
cs.CR11
astro-ph.HE10
cs.CV10
astro-ph.GA9
gr-qc8

The index

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

  1. MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports [arXiv] [episode]
  2. MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation [arXiv] [episode]
  3. Self-Improvement of Large Language Models: A Technical Overview and Future Outlook [arXiv] [episode]
  4. Teaching agentic AI to generalize expert diagnostic reasoning in rare diseases [arXiv] [episode]
  5. Bayesian Empirical Bayes: Simultaneous Inference from Probabilistic Symmetries [arXiv] [episode]
  6. A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problems [arXiv] [episode]
  7. Topology-Aware Differential Privacy in Federated Learning [arXiv] [episode]
  8. A Cosmological Uncertainty Relation and Late-Universe Acceleration [arXiv] [episode]
  9. SHANG++: Robust Stochastic Acceleration under Multiplicative Noise [arXiv] [episode]
  10. Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction [arXiv] [episode]
  11. Unitary quantum matter-bounce in a universe with a positive cosmological constant [arXiv] [episode]
  12. A Fast and Generalizable Fourier Neural Operator-Based Surrogate for Melt-Pool Prediction in Laser Processing [arXiv] [episode]
  13. The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents [arXiv] [episode]
  14. SkillNet: Create, Evaluate, and Connect AI Skills [arXiv] [episode]
  15. Cosmology with the angular cross-correlation of gravitational-wave and galaxy catalogs: forecasts for next-generation interferometers and the Euclid survey [arXiv] [episode]
  16. FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance [arXiv] [episode]
  17. Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training [arXiv] [episode]
  18. GQ-FSL: Green Quantized Federated Split Learning [arXiv] [episode]
  19. Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025 [arXiv] [episode]
  20. Windowed thinning and query complexity for the bouncy particle and Zigzag samplers [arXiv] [episode]
  21. Radiation Reaction effects on Coherent Emission in Relativistic Magnetized Shocks [arXiv] [episode]
  22. Context-Aware Online Conformal Anomaly Detection with Prediction-Powered Data Acquisition [arXiv] [episode]
  23. Probing dipolar power asymmetry with galaxy clustering and intrinsic alignments [arXiv] [episode]
  24. The CTI Echo Chamber: Fragmentation, Overlap, and Vendor Specificity in Twenty Years of Cyber Threat Reporting [arXiv] [episode]
  25. Collective Hallucination in Multi-Agent LLMs:Modeling and Defense [arXiv] [episode]
  26. Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining [arXiv] [episode]
  27. Mask2Real-WM: Controllable Dexterous World Models via Segmentation Masks as a Sim-to-Real Bridge [arXiv] [episode]
  28. Calibrating Adaptive Smoothing Methods for Freeway Traffic Reconstruction [arXiv] [episode]
  29. Large Intestine 3D Shape Refinement Using Point Diffusion Models for Digital Phantom Generation [arXiv] [episode]
  30. On the Emergence of Weak-to-Strong Generalization: A Bias-Variance Perspective [arXiv] [episode]
  31. ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety [arXiv] [episode]
  32. Synthetic Spectral Library of Optically Thick Atmospheres for Little Red Dots [arXiv] [episode]
  33. Thermodynamic behavior of cosmological models with fractional entropy [arXiv] [episode]
  34. Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios [arXiv] [episode]
  35. Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models [arXiv] [episode]
  36. From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning [arXiv] [episode]
  37. SoK: From Silicon to Netlist and Beyond - Two Decades of Hardware Reverse Engineering Research [arXiv] [episode]
  38. The baryonic Tully-Fisher relation as an independent direct probe of cosmology and of the nature of dark matter [arXiv] [episode]
  39. BrainBench: Benchmarking Large Language Models for Comprehensive EEG Understanding [arXiv] [episode]
  40. Gravity with higher-curvature terms and second-order field equations: f(R) meets Gauss-Bonnet [arXiv] [episode]
  41. Theoretical Guarantees for the Subspace-Constrained Tyler's Estimator [arXiv] [episode]
  42. WorldPack: Dynamic Frame Compression for Long-context Video World Modeling [arXiv] [episode]
  43. Planetesimal formation via the streaming instability persists under turbulence driven by magnetorotational instability [arXiv] [episode]
  44. KA2L: A Knowledge-Aware Active Learning Framework for LLMs [arXiv] [episode]
  45. Structured Latent Space Modeling over Multi-Scale Temporal Patches for Multivariate Time Series Forecasting [arXiv] [episode]
  46. Depth-Structured Music Recurrence: Budgeted Recurrent Attention for Full-Piece Symbolic Music Modeling [arXiv] [episode]
  47. Fragility of Value under Imperfect Alignment [arXiv] [episode]
  48. Chaotic Inflation RIDES Again [arXiv] [episode]
  49. Cosmological Dynamics of Multi-Axion Quintessence [arXiv] [episode]
  50. Escaping Local Minima Provably in Non-convex Matrix Sensing: A Deterministic Framework via Simulated Lifting [arXiv] [episode]
  51. The dominance of turbulence over magnetism in the formation of massive star cluster seeds [arXiv] [episode]
  52. Topological Simplification in Predictive Coding Networks [arXiv] [episode]
  53. Enhance the Safety in Reinforcement Learning by ADRC Lagrangian Methods [arXiv] [episode]
  54. Machine Learning Systems: A Survey from a Data-Oriented Perspective [arXiv] [episode]
  55. DeGLIF for Label Noise Robust Node Classification using GNNs [arXiv] [episode]
  56. Hybrid Reinforcement Learning and Search for Flight Trajectory Planning [arXiv] [episode]
  57. Inflationary complexity of thermal state [arXiv] [episode]
  58. THIVLVC: Retrieval Augmented Dependency Parsing for Latin [arXiv] [episode]
  59. Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations [arXiv] [episode]
  60. Automated Computational Energy Minimization of ML Algorithms using Constrained Bayesian Optimization [arXiv] [episode]

Listen

Everything the estate published on 2026-08-20, in the player. Playing from this page is how the edition learns whether anyone did.