The Morning Preprint

Friday 11 September

Showing the most recent batch — Friday 11 September. No papers have been ingested today yet.

793 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: 793 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.

619Mon
1Tue
1740Wed
665Thu
793Fri

Show the answer

793 papers were ingested on Friday 11 September.

793 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG152
cs.AI145
cs.CL89
cs.CR49
cs.CV45
astro-ph.GA28
astro-ph.CO22
astro-ph.HE20

The index

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

  1. Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems [arXiv] [episode]
  2. Longitudinal Risk Prediction in Mammography with Privileged History Distillation [arXiv] [episode]
  3. Chronoberg: A 250-Year Diachronic Corpus with Temporal Affective Lexicons for Language Model Analysis [arXiv] [episode]
  4. A Constraint Programming Approach for n-Day Lookahead Playoff Clinching in the NHL [arXiv] [episode]
  5. Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning [arXiv] [episode]
  6. CQD-SHAP: Explainable Complex Query Answering via Shapley Values [arXiv] [episode]
  7. Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records [arXiv] [episode]
  8. Warranted Attention: Learning What to Pass from Attention to Prediction [arXiv] [episode]
  9. Wiggle and Go! System Identification for Zero-Shot Dynamic Rope Manipulation [arXiv] [episode]
  10. Smoothing the Score Function to Enhance Generalization in Diffusion Models [arXiv] [episode]
  11. RDQ: Residual Distribution Quantization for Large Language Models [arXiv] [episode]
  12. From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents [arXiv] [episode]
  13. LOGIC: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration [arXiv] [episode]
  14. A Density-Matrix Framework for Electronic-Structure Analysis of Electrolytes for Lithium Batteries [arXiv] [episode]
  15. Physics-constrained neural networks for surrogate modeling of lossless periodic structures [arXiv] [episode]
  16. DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum [arXiv] [episode]
  17. Analyzing LLM Reasoning to Uncover Mental Health Stigma [arXiv] [episode]
  18. VeriSim: A Configurable Framework for Stress-Testing Medical AI Under Patient Communication Noise [arXiv] [episode]
  19. How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism [arXiv] [episode]
  20. Four Generations of Quantum Biomedical Sensors [arXiv] [episode]
  21. HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention [arXiv] [episode]
  22. GATTA: Graph Active Learning with Test-Time Augmentation [arXiv] [episode]
  23. TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas [arXiv] [episode]
  24. Physics-Informed Neural Engine Sound Modeling with Differentiable Pulse-Train Synthesis [arXiv] [episode]
  25. Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks [arXiv] [episode]
  26. Generative AI performance in core undergraduate mathematics: a curriculum-level case study [arXiv] [episode]
  27. SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural Representations [arXiv] [episode]
  28. Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling [arXiv] [episode]
  29. Task- and Session-Level Model Routing: A Common-Interface Hybrid Evaluation of Four Open-Source Routers Across Four Benchmarks [arXiv] [episode]
  30. Monotone Neural Policy Iteration for High-Dimensional First-Order Hamilton--Jacobi--Bellman Equations [arXiv] [episode]
  31. EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale [arXiv] [episode]
  32. Semidefinite Programming for Quantum Channel Learning [arXiv] [episode]
  33. DCO: Dynamic Cache Orchestration for LLM Accelerators through Predictive Management [arXiv] [episode]
  34. Federated Learning for Surgical Vision in Appendicitis Classification: Results of the FedSurg EndoVis 2024 Challenge [arXiv] [episode]
  35. A Survey of Threats Against Voice Authentication and Anti-Spoofing Systems [arXiv] [episode]
  36. Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning [arXiv] [episode]
  37. Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups [arXiv] [episode]
  38. AI Economist Agent: An Agentic Framework for Evidence-Based Economic and Financial Analysis with RAG, Knowledge Graphs, and Large Language Models [arXiv] [episode]
  39. A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design [arXiv] [episode]
  40. Assessing Predictive Models for Fairness Based on Activity-Space Patterns [arXiv] [episode]
  41. CLSP-REQA: A Real-Time Quality-Aware Closed-Loop Seizure Prediction Framework with Mamba-BiLSTM and Confidence-Gated Intervention [arXiv] [episode]
  42. 2.5-D Decomposition for LLM-Based Spatial Construction [arXiv] [episode]
  43. Simulating Validity: Modal Decoupling in MLLM Generated Feedback on Science Drawings [arXiv] [episode]
  44. An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc [arXiv] [episode]
  45. Analysis-Driven Procedural Generation of an Engine Sound Dataset with Embedded Control Annotations [arXiv] [episode]
  46. Prediction--Loss Alignment for Sampler--Robust Flow Matching Training [arXiv] [episode]
  47. Reduced NEXI protocol for the quantification of human gray matter microstructure on the Connectome 2.0 scanner [arXiv] [episode]
  48. No Screening is More Efficient with Multiple Objects [arXiv] [episode]
  49. Customized large language models can outperform Community Notes in correcting misinformation [arXiv] [episode]
  50. Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents [arXiv] [episode]
  51. Domain Elastic Transform: Bayesian Function Registration for High-Dimensional Scientific Data [arXiv] [episode]
  52. On the Societal Impact of Machine Learning [arXiv] [episode]
  53. Timely Clinical Diagnosis through Active Test Selection [arXiv] [episode]
  54. Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis [arXiv] [episode]
  55. ScaleResfusion: Residual Rectified Flow based on Residual Vector Field [arXiv] [episode]
  56. Adaptive Perturbation Selection for Contrastive Audio Decoding [arXiv] [episode]
  57. Causal Past Logic for Runtime Verification of Distributed LLM Agent Workflows [arXiv] [episode]
  58. Automated multi-class wound assessment using dedicated instance segmentation models for boundary detection and classification [arXiv] [episode]
  59. mmFHE: mmWave Sensing with End-to-End Fully Homomorphic Encryption [arXiv] [episode]
  60. Quantum Phase Recognition via Quantum Attention Mechanism [arXiv] [episode]

Listen

Everything the estate published on 2026-09-11, in the player. Playing from this page is how the edition learns whether anyone did.