The Morning Preprint

Thursday 10 September

Showing the most recent batch — Thursday 10 September. No papers have been ingested today yet.

665 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: 665 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.

679Fri
619Mon
1Tue
1740Wed
665Thu

Show the answer

665 papers were ingested on Thursday 10 September.

665 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG108
cs.CL100
cs.AI84
cs.CR50
astro-ph.GA39
cs.CV38
astro-ph.HE34
astro-ph.CO21

The index

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

  1. Leveraging Impact Parameter to Mitigate the Transit Light Source Effect: Early Insights from TRAPPIST-1 [arXiv] [episode]
  2. On Scaling Coordinate-Based Neuroevolution: The Quadtree Bottleneck in ES-HyperNEAT [arXiv] [episode]
  3. Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching [arXiv] [episode]
  4. A Planet as the Possible Cause of the HD 181327 Debris Disk Asymmetry [arXiv] [episode]
  5. A Statistical Approach to Estimating Sample Size of Machine Learning Models [arXiv]
  6. An Efficient and Effective Agentic Group Shilling Attack on Recommender Systems [arXiv]
  7. TEFM: Token-Efficient Faithful Modeling for Structured Data [arXiv]
  8. Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning [arXiv]
  9. BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models [arXiv]
  10. Time-Domain Dust Astrophysics. II. TransRAT: Time-Dependent Grain Alignment and Disruption by Cosmic Transients and Their Observational Signatures [arXiv]
  11. High-probability guarantees for linear accessibility in feature superposition [arXiv]
  12. Towards Automatic Evolution Tree Generation from Citation Graphs [arXiv]
  13. Robust Industrial Cyber Physical Classification Using Neuromorphic Temporal Embeddings and Hybrid SNN XGBoost Under Machine Unlearning Attacks [arXiv]
  14. Positional task conditioning for scalable defect detection across product families in large product catalogs [arXiv]
  15. Reproducing Omitted Temporal Expressions in Japanese News for Retrieval-Augmented Applications [arXiv]
  16. Learning with Synthetic Data via SGD in High-Dimensional Linear Regression [arXiv]
  17. Geometric organization of olfactory descriptor data in the Poincar'e disk [arXiv]
  18. When Ad Networks Misbehave: Understanding Risks of Semi-Drive-By Splash Ads [arXiv]
  19. Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features [arXiv]
  20. CityPlanner: A Sandbox Agent for Executable Urban Planning [arXiv]
  21. ECDSA.Fail: Open Autoresearch for Optimizing Elliptic-Curve Point Addition in Shor's Algorithm [arXiv]
  22. Distillation of Synthetic Data for Time Series Foundation Models [arXiv]
  23. Teacher Geometry Shapes Learnability in Teacher-Student Networks [arXiv]
  24. Watermarks Without Verification: AI Text Watermarking After the EU AI Act [arXiv]
  25. Planetary Nebula Central Stars as Tracers of Planetary Nebula-Star Cluster Associations in the Galaxy [arXiv]
  26. Scalable Composition of Byzantine Agreements under Reorder Attacks [arXiv]
  27. Who Are They to Each Other? Multi-Agent Reasoning for Speaker Relationship Inference [arXiv]
  28. A pilot study on the CSST astrometric capability: Detecting astrometric binaries with Gaia synergy via simulated data [arXiv]
  29. LightMedSeg-ISLES: Stroke Lesion Segmentation with 81x Fewer Parameters than nnU-Net [arXiv]
  30. High Resolution Spectroscopic Follow-up Observation Results for 13 EMP Candidates Selected by Narrow-band Photometry [arXiv]
  31. Pulse Signal Simulation of Pulsars [arXiv]
  32. Why Learning Rediscovers the Closed-Form Diagonal Regularizer [arXiv]
  33. Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning [arXiv]
  34. Searching for Type Ia Supernovae in the Dark Energy Spectroscopic Instrument [arXiv]
  35. PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling [arXiv]
  36. Session Attestation for Unmodified TLS Services in Confidential Virtual Machines [arXiv]
  37. SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia [arXiv]
  38. Muon-C: Operator-Aligned Muon for Convolutional Kernels [arXiv]
  39. X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS [arXiv]
  40. Settling: Equilibrium Inference for Non-Convex Validity Sets [arXiv]
  41. An Empirical Study of Development-Tuned Representation Sensitivity for Medical QA Data Selection [arXiv]
  42. ALIGN-HOLD: Experience Alignment for Real-Time Hold Control in Large-Scale Ride-Hailing Matching at DiDi [arXiv]
  43. Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling [arXiv]
  44. When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination [arXiv]
  45. PrivAudit: A Dual-Lens Auditing Framework for Website Privacy Practices under the CCPA [arXiv]
  46. Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph Attacks [arXiv]
  47. A universal connection between lens density profiles and low-frequency wave optics in gravitational-wave lensing [arXiv]
  48. Efficient Graph Neural Networks for Multicarrier Wideband Hybrid Beamforming Optimization [arXiv]
  49. The Evolution of Thermal and Non-thermal Emission Components in GRB 250920C [arXiv]
  50. Scaling E-Commerce Attribute Extraction with Parallel Decoding [arXiv]
  51. StreamAlign: Streaming Text-Aligned Speech Tokenization [arXiv]
  52. EFQ-Softmax: Exp-Free Quantization for Softmax [arXiv]
  53. The FU Ori outburst of PR Ori B [arXiv]
  54. Aarmed with Data: Bumps, Outflows, and Disk-like Emission in TDE 2025aarm [arXiv]
  55. EEGBind: Detecting Source-Level Interictal Epileptiform Discharges via EEG-Centric Multimodal Binding [arXiv]
  56. CROCODILE-SIDM: Tidal Formation of Dark Matter-Deficient Galaxies as a Test Case [arXiv]
  57. Automated Detection of Double-Lined Spectroscopic Binaries in High-Resolution Spectra and a Probabilistic Analysis of Stellar Multiplicity [arXiv]
  58. Can Artificial Intelligence Support Healthcare and Mental Health Through Early Cyberbullying Detection ? The Impact of Emotion-Aware AI on Proactive Online Safety [arXiv]
  59. MethaneFuse: Learning from Multi-Sensor Satellite Observations for Methane Plume Detection [arXiv]
  60. 1LHAASO J1852+0050u: GeV-100TeV Gamma-ray emission Powered by Star-forming Region? [arXiv]

Listen

Everything the estate published on 2026-09-10, in the player. Playing from this page is how the edition learns whether anyone did.