The Morning Preprint

Tuesday 29 September

Showing the most recent batch — Tuesday 29 September. No papers have been ingested today yet.

3432 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.

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.

768Wed
4209Thu
1231Fri
1Sat
1135Mon
3432Tue

Show the answer

3432 papers were ingested on Tuesday 29 September.

3432 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG637
cs.CV636
cs.AI397
cs.CL337
cs.RO256
quant-ph221
cs.CR111
stat.ML73

The index

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

  1. BRST quantization for the restoration of broken symmetries: a pedagogical example [arXiv] [episode]
  2. A Survey on Efficient Vision-Language-Action Models [arXiv] [episode]
  3. LitReview Arena: Evaluating Literature Review Agents with Battle-Style Peer Review Platform [arXiv] [episode]
  4. Transport in the emergent Bose liquid: Bad metal, strange metal, and weak insulator, all in one system [arXiv] [episode]
  5. Vigil: Accountable Liveness against Selective Silence [arXiv] [episode]
  6. Robust 3D Reconstruction from Multi-View Optical Satellite Imagery via Reliability-Aware Height-Evidence Fusion in Gaussian Splatting [arXiv] [episode]
  7. Wavelength-Uniform Quantum Algorithms for Mixed-State Quantum Dynamics [arXiv] [episode]
  8. UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City [arXiv] [episode]
  9. Physics-Constrained Deep Learning Model for Contactless Blood Pressure Monitoring from Triaxial Bodyseismography [arXiv] [episode]
  10. Compact Feed-Forward 3D Gaussians via Saliency-Guided Primitive Merging [arXiv] [episode]
  11. OmniVR: Audio-Video Conditional Generation for Archival Footage Restoration [arXiv] [episode]
  12. InferScale: GPU-Native KV Injection for Personalized LLM Serving [arXiv] [episode]
  13. Sharp continuity of quantum conditional entropy [arXiv] [episode]
  14. MOPDA: Mixed-Trajectory On-Policy Distillation for Language-Guided Industrial Anomaly Detection [arXiv] [episode]
  15. Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment [arXiv] [episode]
  16. Collapse and Inversion of the Josephson Potential in a Strongly Driven Superconducting Circuit [arXiv] [episode]
  17. Absolute frequency measurement of a 176 Lu+,(cubed D 1) standard against the NRC-FCs2 fountain with 2.6 times10-16 uncertainty [arXiv] [episode]
  18. Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification [arXiv] [episode]
  19. Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation [arXiv] [episode]
  20. Making AI Scientists Auditable from Evidence to Claim [arXiv] [episode]
  21. Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness [arXiv] [episode]
  22. AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents [arXiv] [episode]
  23. ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages [arXiv] [episode]
  24. Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding [arXiv] [episode]
  25. Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis [arXiv] [episode]
  26. GeoMetric: Injecting Metric Geographic Structure into Worldwide Image Geo-Localization [arXiv] [episode]
  27. Inside the LLM Word Factory [arXiv] [episode]
  28. Vault: One-Step Latent Generation with Positive-Anchored Rewards for Autonomous Driving [arXiv] [episode]
  29. The bulk spectral gap is certifiable from above but uncomputable from below [arXiv] [episode]
  30. Quantifying and Mitigating Domain Shift in Peach Leaf Damage Classification: Attention Mechanisms and Fine-Tuning Strategies [arXiv] [episode]
  31. Knowledge-Intensive Video Generation [arXiv] [episode]
  32. Accelerated "on-the-fly" coupled-cluster path-integral molecular dynamics: Impact of nuclear quantum effects on an asymmetric proton [arXiv] [episode]
  33. PoisonCap: Efficient Hierarchical Temporal Safety for CHERI [arXiv] [episode]
  34. Universal Spin Squeezing Dynamical Phase Transitions across Lattice Geometries, Dimensions, and Microscopic Couplings [arXiv] [episode]
  35. Deep Minds and Shallow Probes [arXiv] [episode]
  36. delta-mem: Efficient Online Memory for Large Language Models [arXiv] [episode]
  37. Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs [arXiv] [episode]
  38. PACE: Policy-Native Adaptive Decision Timing for Long-Horizon Reasoning [arXiv] [episode]
  39. MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image [arXiv] [episode]
  40. Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning [arXiv] [episode]
  41. How LLMs Are Persuaded: A Few Attention Heads, Rerouted [arXiv] [episode]
  42. FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning [arXiv] [episode]
  43. RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation [arXiv] [episode]
  44. In-Context Credit Assignment via the Core [arXiv] [episode]
  45. Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility [arXiv] [episode]
  46. Efficient Quantum Fourier Transforms For Semisimple Algebras [arXiv] [episode]
  47. MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents [arXiv] [episode]
  48. Algebraic quantum kinematics: Galilean covariance with positive energy confines unequal-time commutation to null sets [arXiv] [episode]
  49. AVICA: A fully automated CASA pipeline for large volume VLBI data calibration [arXiv] [episode]
  50. OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning [arXiv] [episode]
  51. Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF [arXiv] [episode]
  52. IndexRAG: Index-Time Reasoning for Multi-Hop Retrieval-Augmented Generation [arXiv] [episode]
  53. Dimensional reduction by singlet blockade in the distorted kagome magnet YCa 3 (CrO) 3 (BO 3) 4 [arXiv] [episode]
  54. Code2Math: Can Your Code Agent Evolve Math Problems Through Exploration? [arXiv] [episode]
  55. Toward Robust, Reproducible, and Widely Accessible Intracranial Speech Brain-Computer Interfaces: A Comprehensive Narrative Review of Neural Mechanisms, Hardware, Algorithms, Evaluation, Clinical Pathways and Future Directions [arXiv] [episode]
  56. InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation [arXiv] [episode]
  57. MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics [arXiv] [episode]
  58. Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generative Modeling [arXiv] [episode]
  59. Watch the Model Think: On-Policy Extraction of Activation Steering Vectors [arXiv] [episode]
  60. Stable Velocity: A Variance Perspective on Flow Matching [arXiv] [episode]

Listen

Everything the estate published on 2026-09-29, in the player. Playing from this page is how the edition learns whether anyone did.