The Morning Preprint

Monday 7 September

Showing the most recent batch — Monday 7 September. No papers have been ingested today yet.

619 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: 619 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.

1650Tue
956Wed
666Thu
679Fri
619Mon

Show the answer

619 papers were ingested on Monday 7 September.

619 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.AI126
cs.LG117
cs.CL91
cs.CV36
cs.CR34
astro-ph.EP26
astro-ph.GA26
astro-ph.CO20

The index

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

  1. NORi: An ML-Augmented Ocean Boundary Layer Parameterization [arXiv] [episode]
  2. Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor [arXiv] [episode]
  3. Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving [arXiv] [episode]
  4. SoK: AI-Augmented Binary Reversing [arXiv] [episode]
  5. SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control [arXiv] [episode]
  6. AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories [arXiv] [episode]
  7. A Novel kinetic Sunyaev-Zel'dovich Estimator for Electron-Electron Correlations [arXiv] [episode]
  8. Efficient Fuzzy PSI under One-Sided Assumptions [arXiv] [episode]
  9. Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats [arXiv] [episode]
  10. Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs [arXiv] [episode]
  11. SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision [arXiv] [episode]
  12. Scientific Domain Knowledge Improves Vision-Language Fundus Models [arXiv] [episode]
  13. Numerical Studies of Accretion Flows onto a Neutron Star Engulfed in a Massive Star [arXiv] [episode]
  14. X-VC: Zero-shot Streaming Voice Conversion in Codec Space [arXiv] [episode]
  15. A New Approach to Code Smoothing Bounds [arXiv] [episode]
  16. Hybrid Model Predictive Control with Physics-Informed Neural Network for Satellite Attitude Control [arXiv] [episode]
  17. TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation [arXiv] [episode]
  18. ConfRAG: Confidence-Guided Retrieval-Augmenting Generation [arXiv] [episode]
  19. AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports [arXiv] [episode]
  20. TRNet: Learning with Topographic Priors for VHR Paddy Rice Mapping [arXiv] [episode]
  21. Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes [arXiv] [episode]
  22. To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion [arXiv] [episode]
  23. Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers [arXiv] [episode]
  24. Consensus Group Relative Policy Optimization for Text Generation [arXiv] [episode]
  25. A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions [arXiv] [episode]
  26. Improving Weak World Models Behind Strong Agents in Atari Pong [arXiv] [episode]
  27. Longitudinal Adoption and Deprecation of the Privacy Sandbox Web APIs [arXiv] [episode]
  28. Advancing Subseasonal Forecasting with Machine Learning [arXiv] [episode]
  29. Unified Deployment-Aware Evaluation of Open Reasoning Language Models [arXiv] [episode]
  30. Mapping Dark-Matter Clusters via Physics-Guided Diffusion Models [arXiv] [episode]
  31. RL-VLA cubed: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training [arXiv] [episode]
  32. High-dimensional censored MIDAS logistic regression for corporate survival forecasting [arXiv] [episode]
  33. Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation [arXiv] [episode]
  34. EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents [arXiv] [episode]
  35. Second-order consistency for learning chaotic dynamics via randomized Jacobian matching [arXiv] [episode]
  36. Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning [arXiv] [episode]
  37. Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection [arXiv] [episode]
  38. GAME: Genetic Algorithms with Marginalised Ensembles for model-independent reconstruction of cosmological quantities [arXiv] [episode]
  39. Multi-Modal Time Series Prediction via Mixture of Modulated Experts [arXiv] [episode]
  40. Naturally small Dirac neutrino mass and B-L dark matter [arXiv] [episode]
  41. Beyond Reproducibility: Token Probabilities Expose Large Language Model Nondeterminism [arXiv] [episode]
  42. Mass dependence of halo baryon fractions from the kinetic Sunyaev-Zeldovich effect [arXiv] [episode]
  43. Deep Learning-Driven Peptide Classification in Biological Nanopores [arXiv] [episode]
  44. A Survey on Semantic Modeling for Building Energy Management [arXiv] [episode]
  45. Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring [arXiv] [episode]
  46. From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data [arXiv] [episode]
  47. Enhancing Affine Maximizer Auctions with Correlation-Aware Payment [arXiv] [episode]
  48. Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points [arXiv] [episode]
  49. ClosureBench: A Constructive Benchmark for Compositional Graph Reasoning [arXiv] [episode]
  50. Boosting Data Augmentation with Stochastic Weight Averaging [arXiv] [episode]
  51. Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings [arXiv] [episode]
  52. Puzzling Ultra-Diffuse Galaxy Evolution (PUDGE). II. A transformation pathway from ultra-diffuse galaxies to compact dwarfs in galaxy clusters [arXiv] [episode]
  53. Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation [arXiv] [episode]
  54. Study of neutrino spin oscillations in a gravitational field with a differential equations method [arXiv] [episode]
  55. Topological dark energy from spacetime foam: A challenge for CDM [arXiv] [episode]
  56. The Sample Complexity of Learning Lipschitz Operators with respect to Gaussian Measures [arXiv] [episode]
  57. Behind the Mask: can HARMONI@ELT detect biosignatures in the reflected light of Proxima b? [arXiv] [episode]
  58. Rogue Ones: Orbital census of Galactic Cepheids and their Anomalies [arXiv] [episode]
  59. Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models [arXiv] [episode]
  60. Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning [arXiv] [episode]

Listen

Everything the estate published on 2026-09-07, in the player. Playing from this page is how the edition learns whether anyone did.