The Morning Preprint

Monday 14 September

Showing the most recent batch — Monday 14 September. No papers have been ingested today yet.

588 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: 588 papers against a busiest day of 1740 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.

1Tue
1740Wed
665Thu
793Fri
588Mon

Show the answer

588 papers were ingested on Monday 14 September.

588 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG133
cs.AI90
cs.CL70
cs.CR40
cs.CV28
astro-ph.GA23
astro-ph.HE19
cs.RO13

The index

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

  1. UltraQuant: 4-bit KV Caching for Context-Heavy Agents [arXiv] [episode]
  2. Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models [arXiv] [episode]
  3. Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation [arXiv] [episode]
  4. GigaBrain-WBC-0.5: A Behavior World Model for Robust Humanoid Whole-Body Tracking with Environment Interaction [arXiv] [episode]
  5. PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement [arXiv] [episode]
  6. ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning [arXiv] [episode]
  7. DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models [arXiv] [episode]
  8. LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization [arXiv] [episode]
  9. AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally [arXiv] [episode]
  10. A unified self-supervised framework for single-frame Fresnel CDI and overlapped ptychography [arXiv] [episode]
  11. A Mechanism-Coupled Split Window Network for Medium- to High-Resolution Land Surface Temperature Retrieval [arXiv] [episode]
  12. Unified Text-Image Generation with Weakness-Targeted Post-Training [arXiv] [episode]
  13. Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval [arXiv] [episode]
  14. ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions [arXiv] [episode]
  15. Cooling of Isolated Neutron Stars with Hyperon-mixed Kaon-Condensation Matter [arXiv] [episode]
  16. MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models [arXiv] [episode]
  17. Mapping Partisan Fault Lines Within DAOs [arXiv] [episode]
  18. Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models [arXiv] [episode]
  19. FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data [arXiv] [episode]
  20. Robust Trust [arXiv] [episode]
  21. Measuring Pragmatic Influence in Large Language Model Instructions [arXiv] [episode]
  22. A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients [arXiv] [episode]
  23. CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval [arXiv] [episode]
  24. Hurdle-RMIL: Addressing Zero Inflation and Long-Tailed Imbalance in Infrared Rainfall Retrieval [arXiv] [episode]
  25. Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? [arXiv] [episode]
  26. Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills [arXiv] [episode]
  27. UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures [arXiv] [episode]
  28. OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots [arXiv] [episode]
  29. Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases [arXiv] [episode]
  30. X-ray Analysis of Gamma-Ray Burst Flares and Underlying Afterglows: Insights into Origin of Flares [arXiv] [episode]
  31. DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Prediction [arXiv] [episode]
  32. Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment [arXiv] [episode]
  33. ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems [arXiv] [episode]
  34. Representation Before Training: A Practical Benchmark for Generative Medical Event Model Tokenization [arXiv] [episode]
  35. PACE: A Neuro-Symbolic Framework for Plausible and Actionable Counterfactual Explanations [arXiv] [episode]
  36. Hedorah, the first yellow supergiant Kaiju star candidate at z=3.7 revealed by JWST behind AS1063 [arXiv] [episode]
  37. Generative AI Assisted Workflows in Architectural Conceptual Design: Performance, Creative Self-Efficacy, and Cognitive Load [arXiv] [episode]
  38. From Stealthy Data Fabrication to Unsafe Driving: Realistic Scenario Attacks on Collaborative Perception [arXiv] [episode]
  39. ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces [arXiv] [episode]
  40. Hessian-based photometric substructure as an evolutionary tracer of OB cluster candidates in M31 [arXiv] [episode]
  41. Generation of TeV Photons by PeV Neutrinos in Dense Astrophysical Environments [arXiv] [episode]
  42. Implications of the LISA stochastic signal from eccentric stellar mass black hole binaries in vacuum [arXiv] [episode]
  43. Project Rachel: Can an AI Become a Scholarly Author? [arXiv] [episode]
  44. The dynamics of the Anglerfish cluster [arXiv] [episode]
  45. From Automata Learning to Model Checking: Formal Security Verification of Black-Box Protocols [arXiv] [episode]
  46. Gas distributions inside and around haloes in the alternative dark matter simulations AIDA-TNG [arXiv] [episode]
  47. Federated Learning in the Wild: A Comparative Study for Cybersecurity under Non-IID and Unbalanced Settings [arXiv] [episode]
  48. Mass-Orbital Period Distribution of Massive White Dwarfs Formed Through Stable Mass Transfer [arXiv] [episode]
  49. The Power of DESI for Photometric Redshift Calibration: A Case Study with KiDS-1000 [arXiv]
  50. Securing People and their Machines Against Major Faults [arXiv] [episode]
  51. ABCMB: A Python+JAX Package for the Cosmic Microwave Background Power Spectrum [arXiv] [episode]
  52. Induced Scattering of Strong Waves in Pair Plasmas [arXiv] [episode]
  53. Branching Universes [arXiv] [episode]
  54. Mass and Spin Growth of Very Massive Stars in Star Clusters Potentially Associated with Little Red Dots [arXiv] [episode]
  55. The Heavy Tailed Non-Gaussianity of the Supermassive Black Hole Gravitational Wave Background [arXiv] [episode]
  56. BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines [arXiv] [episode]
  57. Probing Two-dimensional Asymmetries of an Exoplanet Atmosphere from Chromatic Transit Variation [arXiv] [episode]
  58. Lagrangian Identity and Mass Evolution of Particle-like Objects in Nonminimally Coupled Gravity [arXiv] [episode]
  59. The quasi-star model for Little Red Dots: potential and challenges [arXiv] [episode]
  60. On the Theory of Bulk Viscosity of Cold Plasmas and Thermodynamics of Alkali-Noble Gas Cocktails [arXiv] [episode]

Listen

Everything the estate published on 2026-09-14, in the player. Playing from this page is how the edition learns whether anyone did.