The Morning Preprint

Friday 21 August

Showing the most recent batch — Friday 21 August. No papers have been ingested today yet.

199 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: 199 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.

475Mon
432Tue
52Wed
186Thu
199Fri

Show the answer

199 papers were ingested on Friday 21 August.

199 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG56
cs.CL21
cs.AI15
astro-ph.CO12
astro-ph.HE11
cs.CV11
cs.CR7
cs.RO7

The index

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

  1. FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning [arXiv] [episode]
  2. Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization [arXiv] [episode]
  3. TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning [arXiv] [episode]
  4. VERSUS: An excursion-set-inspired void-finder for the Stage-IV era [arXiv] [episode]
  5. ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis [arXiv] [episode]
  6. Guided Diffusion by Optimized Loss Functions on Relaxed Parameters for Inverse Material Design [arXiv] [episode]
  7. Audit Before You Update: Recording Artifacts and the Limits of Bounded Model Updates in MIMIC-IV ICU Prediction [arXiv] [episode]
  8. Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval [arXiv] [episode]
  9. Towards Formalizing Reinforcement Learning Theory [arXiv] [episode]
  10. Qworld: Question-Specific Evaluation Criteria for LLMs [arXiv] [episode]
  11. Towards Audio Token Compression in Large Audio Language Models [arXiv] [episode]
  12. Generative AI Use in Entrepreneurship: An Integrative Review and an Empowerment-Entrapment Framework [arXiv] [episode]
  13. ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU [arXiv] [episode]
  14. White dwarf + M dwarf Detached Binaries in Long Period Radio Transients: Observed Binary Parameters, Evolution, and Population Constraints [arXiv] [episode]
  15. Vacuum birefringence and the polarized X-ray emission from a radio magnetar [arXiv] [episode]
  16. Your Turn: At Home Turning Angle Estimation for Parkinson's Disease Severity Assessment [arXiv] [episode]
  17. HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings [arXiv] [episode]
  18. ReynoldsFlow: Exquisite Flow Estimation via Reynolds Transport Theorem [arXiv] [episode]
  19. From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering [arXiv] [episode]
  20. Learning-Augmented Power System Operations: A Unified Optimization View [arXiv] [episode]
  21. Boson star-black hole binaries: initial data and head-on collisions [arXiv] [episode]
  22. Can Predicted Dynamics Exist in the Physical World? [arXiv] [episode]
  23. Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering [arXiv] [episode]
  24. CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics [arXiv] [episode]
  25. A Distributional Robustness Margin For Pathology Foundation Models [arXiv] [episode]
  26. Structural Analysis of a Scalar-Tensor Realization of Interacting Dark Energy [arXiv] [episode]
  27. FinVerse: Financial Time-Series Benchmark [arXiv] [episode]
  28. Extended to Reality: Prompt Injection in 3D Environments [arXiv] [episode]
  29. Trustworthy scientific inference with generative models [arXiv] [episode]
  30. SPINEX-Clustering: Similarity-based Predictions with Explainable Neighbors Exploration for Clustering Problems [arXiv] [episode]
  31. Why Can't I See My Clusters? A Precision-Recall Approach to Dimensionality Reduction Validation [arXiv] [episode]
  32. Conformal novelty detection with false discovery rate control at the boundary [arXiv] [episode]
  33. HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models [arXiv] [episode]
  34. Perturbative and numerical study of nonlinear relativistic effects in weak lensing [arXiv] [episode]
  35. A Robust Foundation Model for Conservation Laws: Injecting Context into Flux Neural Operators via Recurrent Vision Transformers [arXiv] [episode]
  36. Positive-Data Learning of Fixed-Observation Linear MCFGs from Working Binary Presentations [arXiv] [episode]
  37. Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation [arXiv] [episode]
  38. Evolution of Log-Based Detection Rules in Public Repositories [arXiv] [episode]
  39. Critic-Free Deep Reinforcement Learning for Maritime Coverage Path Planning on Irregular Hexagonal Grids [arXiv] [episode]
  40. ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning [arXiv] [episode]
  41. Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion [arXiv] [episode]
  42. Improving Requirements Classification with SMOTE-Tomek Preprocessing [arXiv] [episode]
  43. Better Call Graphs: A New Dataset of Function Call Graphs for Malware Classification [arXiv] [episode]
  44. Partition of Unity Neural Networks for Interpretable Classification with Explicit Class Regions [arXiv] [episode]
  45. Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems [arXiv] [episode]
  46. Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement [arXiv] [episode]
  47. Self-Harness: Harnesses That Improve Themselves [arXiv] [episode]
  48. Mapping AI Programs in the U.S: A Status Report from Early 2026 and an Analysis of AI Majors and Minors [arXiv] [episode]
  49. Geometric Evolution Maps: Extracting Stable Concept Probes from Transformer Residual Streams [arXiv] [episode]
  50. The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction [arXiv] [episode]
  51. Beyond Prediction: Interval Neural Networks for Uncertainty-Aware System Identification [arXiv] [episode]
  52. Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents [arXiv] [episode]
  53. The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence [arXiv] [episode]
  54. Iterative Improvement of an Additively Regularized Topic Model [arXiv] [episode]
  55. PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models [arXiv] [episode]
  56. DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition [arXiv] [episode]
  57. GridCodex: A RAG-Driven AI Framework for Power Grid Code Reasoning and Compliance [arXiv] [episode]
  58. Neural Prior Estimation: Learning Class Priors from Latent Representations [arXiv] [episode]
  59. RepSelect: Robust LLM Unlearning via Representation Selectivity [arXiv] [episode]
  60. The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth [arXiv] [episode]

Listen

Everything the estate published on 2026-08-21, in the player. Playing from this page is how the edition learns whether anyone did.