The Morning Preprint

Monday 24 August

Showing the most recent batch — Monday 24 August. No papers have been ingested today yet.

173 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: 173 papers against a busiest day of 432 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.

432Tue
52Wed
186Thu
199Fri
173Mon

Show the answer

173 papers were ingested on Monday 24 August.

173 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG40
cs.CL28
cs.AI17
cs.CV12
astro-ph.CO9
cs.CR8
stat.ME5
astro-ph.HE4

The index

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

  1. Angular clustering and bias of photometric quasars in the Kilo-Degree Survey Data Release 4 [arXiv] [episode]
  2. AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning [arXiv] [episode]
  3. SCOPE: A Generative Approach for LLM Prompt Compression [arXiv] [episode]
  4. Doubly robust inference via calibration [arXiv] [episode]
  5. A signal dedispersion algorithm for imaging-based transient searches [arXiv] [episode]
  6. BRAVA-GNN: Betweenness Ranking Approximation Via Degree MAss Inspired Graph Neural Network [arXiv] [episode]
  7. Compared to What? Baselines and Metrics for Counterfactual Prompting [arXiv] [episode]
  8. MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation [arXiv] [episode]
  9. Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS [arXiv] [episode]
  10. Wings of little dots: Exponential broad lines from a stratified BLR [arXiv] [episode]
  11. SN 2022riv in RX J2129: Discovery, Spectroscopic Classification, and Microlensing of a Strongly Lensed Type Ia Supernova from JWST and HST Observations [arXiv] [episode]
  12. PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval [arXiv] [episode]
  13. Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering [arXiv] [episode]
  14. Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature [arXiv] [episode]
  15. From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems [arXiv] [episode]
  16. Quantum Oracle Distribution Switching and Applications to Falcon and Ring Signatures [arXiv] [episode]
  17. MemPromptTSS: Persistent Prompt Memory for Iterative Multi-Granularity Time Series State Segmentation [arXiv] [episode]
  18. Topological Detection of Hopf Bifurcations via Persistent Homology: A Functional Criterion from Time Series [arXiv] [episode]
  19. Scale or Reason? A Compute-Equivalent Analysis of Reasoning Distillation [arXiv] [episode]
  20. Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries [arXiv] [episode]
  21. Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design [arXiv] [episode]
  22. The Extreme Quasar Main Sequence of Super-Eddington DESI-DR1 NLSy1 Galaxies [arXiv] [episode]
  23. A Hybrid Intrusion Detection System for Electric Vehicle Charging Infrastructure [arXiv] [episode]
  24. Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models [arXiv] [episode]
  25. Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations [arXiv] [episode]
  26. Interpretability in Deep Time Series Models Demands Semantic Alignment [arXiv] [episode]
  27. Index SLM Technical Report [arXiv] [episode]
  28. ALMA measurements of mass loss and wind clumping in the massive stars of the Arches cluster [arXiv] [episode]
  29. Smart Exploration in Reinforcement Learning using Bounded Uncertainty Models [arXiv] [episode]
  30. GeoGuess: Multimodal Reasoning based on Hierarchy of Visual Information in Street View [arXiv] [episode]
  31. SEISMO: Increasing Sample Efficiency in Molecular Optimization with a Trajectory-Aware LLM Agent [arXiv] [episode]
  32. Granuscore: A Reference-Free Measure of Granularity for Text Analysis and Question Answering [arXiv] [episode]
  33. Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence [arXiv] [episode]
  34. Action-grounded tissue affordance enables anticipatory auto-framing that lowers surgeon cognitive workload during laparoscopic surgery [arXiv] [episode]
  35. Shoot from the HIP: Hessian Interatomic Potentials without derivatives [arXiv] [episode]
  36. CFM: Language-aligned Concept Foundation Model for Vision [arXiv] [episode]
  37. DKD-KAN: A Lightweight knowledge-distilled KAN intrusion detection framework, based on MLP and KAN [arXiv] [episode]
  38. "Elementary, My Dear Watson." Detecting Malicious Skills via Neuro-Symbolic Reasoning across Heterogeneous Artifacts [arXiv] [episode]
  39. Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization [arXiv] [episode]
  40. Audio Interaction Model [arXiv] [episode]
  41. DESIVAST: A Catalog of Low-Redshift Voids using Data from the DESI DR1 Bright Galaxy Survey [arXiv] [episode]
  42. Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks [arXiv] [episode]
  43. The Generalization Ridge: Information Flow in Natural Language Generation [arXiv] [episode]
  44. Aligning Human-AI-Interaction Trust for Mental Health Support: Survey and Position for Multi-Stakeholders [arXiv] [episode]
  45. Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows [arXiv] [episode]
  46. S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning [arXiv] [episode]
  47. GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents [arXiv] [episode]
  48. FeLoG: Scalable and Efficient Distributed Graph Embedding with Feedback Loop Mechanism [arXiv] [episode]
  49. Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation [arXiv] [episode]
  50. Integrability of R squared gravity cosmological models with radiation [arXiv] [episode]
  51. Adaptive Inference for Resource-Constrained Dynamic Pricing [arXiv] [episode]
  52. MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation [arXiv] [episode]
  53. SPD Matrix Learning for Neuroimaging Analysis: Perspectives, Methods, and Challenges [arXiv] [episode]
  54. Double Machine Learning of Continuous Treatment Effects with General Instrumental Variables [arXiv] [episode]
  55. ZenGen: Social Mind for LLMs [arXiv] [episode]
  56. Building a Functional Machine Translation Corpus for Kpelle [arXiv] [episode]
  57. Distributed, communication-efficient, and differentially private estimation of KL divergence [arXiv] [episode]
  58. Can LLMs Introspect? A Reality Check [arXiv] [episode]
  59. MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents [arXiv] [episode]
  60. Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effect [arXiv] [episode]