The Morning Preprint

Tuesday 22 September

Showing the most recent batch — Tuesday 22 September. No papers have been ingested today yet.

1387 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.

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.

676Wed
743Thu
747Fri
568Mon
1387Tue

Show the answer

1387 papers were ingested on Tuesday 22 September.

1387 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG311
cs.CL235
cs.AI165
cs.CV87
cs.CR79
cs.RO57
astro-ph.GA54
astro-ph.HE38

The index

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

  1. Astrobiology and the Transformation of Scientific Epistemology [arXiv] [episode]
  2. Djinnlang: Higher-Level Programming by Unambiguous Specification with an LLM in the Compiler [arXiv]
  3. Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs [arXiv]
  4. Regime transitions of dynamos driven by fingering double-diffusive convection [arXiv]
  5. Divergent strategies and convergent outcomes in autonomous materials discovery [arXiv]
  6. Open-Jev Judgments on CallScreenBench: Calibrated One-Pass Scam Screening with a Small Language Model [arXiv]
  7. Satellite Survival through Gas Redistribution in a Low-viscosity Disk [arXiv]
  8. From Tables to Quantified Statements: Evaluating LLM Inference Generation through Executable Verification [arXiv]
  9. Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter? [arXiv]
  10. Exponential Family Synthetic Controls [arXiv]
  11. UniK: Universal Knowledge Perception for Digital and Physical AI [arXiv]
  12. LEAP-NBV: Lightweight Edge Active-Perception for Foundation-Model Next-Best-View Planning [arXiv]
  13. AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models [arXiv]
  14. MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes [arXiv]
  15. The CAMELS-CROCODILE Simulation Suite: A New Cosmology--Astrophysics Playground for Machine Learning [arXiv]
  16. Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents [arXiv]
  17. The Operational Value of Spatial Dependence in Renewable Forecast Scenarios for Single-Period Economic Dispatch: A Controlled Ablation Study [arXiv]
  18. ACLArena: Agent Continue Learning in Multi-stage Post-training [arXiv]
  19. MGRD: Compact morphology-gated residual diffusion for variance-aware cross-domain neurite forecasting [arXiv]
  20. Simpler Methods Work Better for L1 Penalized Logistic Models and Large Datasets [arXiv]
  21. RoboTalk: Learning Multi-Robot Communication and Coordination from Multimodal Demonstrations [arXiv]
  22. Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models [arXiv]
  23. FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering [arXiv]
  24. ShapeLex: Decoupling Local Shape Symbolization and Global Scale Modeling for Text-Controlled Time Series Generation [arXiv]
  25. AT2019aalc: An obscured tidal disruption event candidate in an active galactic nucleus revealed by its first flare? [arXiv]
  26. The Common Envelope Evolution Outcome. III. the Improvement of Stellar Binding Energy with the Envelope Residual [arXiv]
  27. Testing, not presuming, adequacy: calibrating generative social simulators against emergent network structure [arXiv]
  28. Context-Aware Pre-Deployment Evaluation of AI Systems: A Regulatory Framework for Nigerian Fintech [arXiv]
  29. Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver [arXiv]
  30. Synthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search [arXiv]
  31. InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection [arXiv]
  32. When Evidence Conflicts: Reliability-aware Meta-review Generation [arXiv]
  33. Structured Decomposition for Reliable LLM-Generated Access Control Policies [arXiv]
  34. Graph-to-Grid (G2G): Continuous-Coordinate Feature Painting for Soccer Pass Surfaces [arXiv]
  35. Q-DEQ: Discrete Solving and Quantization for Deep Equilibrium Models in Time Series Forecasting under Edge Deployment Coding Constraints [arXiv]
  36. Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev) [arXiv]
  37. Representation-guided in-context learning for medical image interpretation with multimodal large language models [arXiv]
  38. A Sample of 459 Galaxy Groups Identified from the FAST All Sky HI Survey DR2 [arXiv]
  39. MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification [arXiv]
  40. Vision Transformers versus convolutional neural networks for fine-grained orchid genus identification in a species-rich, data-poor flora: a controlled benchmark on the Orchidaceae of New Guinea [arXiv]
  41. Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance [arXiv]
  42. LeaseGuard: Incumbent-Preserving Admission Control for Privileged LLM Agents [arXiv]
  43. From Content Generation to Learning Support: Pedagogy-Guided Generative Video Tutors for STEM Learning [arXiv]
  44. From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models [arXiv]
  45. Constraints on Axion-like Dark Matter from Cosmic Birefringence with a Polarization Array of Repeating Fast Radio Bursts [arXiv]
  46. Doubly robust target inference for generalized linear regression with completely missing covariates [arXiv]
  47. FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention [arXiv]
  48. Incremental Consistency Execution for Autonomous Intelligent Systems [arXiv]
  49. DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents [arXiv]
  50. WidgetVA: A Widget-Centric Framework and Benchmark for Agentic Visual Analytics [arXiv]
  51. When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search [arXiv]
  52. Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective [arXiv]
  53. You Can Tell Who's Asking: What the Web's Questions Are Made Of, and Where They Come From [arXiv]
  54. SPeaR: Test-Time Adaptation with Steering Primitives for Realigning Representations [arXiv]
  55. Causal Bayesian Optimization: Foundations, Methods, and Applications [arXiv]
  56. EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation [arXiv]
  57. PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems [arXiv]
  58. Re:CAP - Auditing Retrieval Coverage in Production RAG Pipelines [arXiv]
  59. ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation [arXiv]
  60. Model-Agnostic Feature Selection via LOCO-Guided Adaptive Minipatch Sampling [arXiv]

Listen

Everything the estate published on 2026-09-22, in the player. Playing from this page is how the edition learns whether anyone did.