The Morning Preprint

Thursday 17 September

Showing the most recent batch — Thursday 17 September. No papers have been ingested today yet.

743 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.

793Fri
588Mon
1326Tue
676Wed
743Thu

Show the answer

743 papers were ingested on Thursday 17 September.

743 papers, three ways

Where today's batch landed

By the paper's primary arXiv category.
cs.LG152
cs.CL115
cs.AI89
cs.CR43
cs.CV39
astro-ph.GA30
astro-ph.HE24
cs.RO24

The index

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

  1. On the Identifiability of Mixed Ordinal and Exponential Family Causal DAGs under Linear Parametric Models [arXiv]
  2. ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference [arXiv]
  3. Maximum Strong Independent Sets in Hypergraphs: Reductions, Bounds, and Greedy Certificates [arXiv]
  4. EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing [arXiv]
  5. TACTICS: Taxonomy-Aware Intelligent Corpus Sampling for Machine Translation [arXiv]
  6. Mixed-Integer Nonlinear Differentiable Predictive Control for Underground Pumped Hydro Energy Storage Systems [arXiv]
  7. Measuring AI Leadership: Development and Validation of a Multidimensional Measure for AI-Native Organizations [arXiv]
  8. Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI [arXiv]
  9. Matching Multi-Loop Complexities with a Single Loop: Optimal Optimization Stationarity and Best-Known Game Stationarity in Nonconvex--Concave Minimax Optimization [arXiv]
  10. When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI [arXiv]
  11. Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs [arXiv]
  12. Contiguity, Not Importance: Budgeted Repair of Stale KV Caches After Document Edits [arXiv]
  13. TuiML: Machine Learning for AI Agents [arXiv]
  14. RideWay: Benchmarking Efficient Task Completion for Tool-Using Language Agents [arXiv]
  15. Multimodal Conditioning of Fine-Tuned Stable Diffusion XL for Controllable and Culturally Faithful Ulos Motif Generation [arXiv]
  16. Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders [arXiv]
  17. Fourier Analysis of Parametrized Interactive Quantum Classifiers [arXiv]
  18. The Operable Pareto Front: Distilling Offline Search into Run-Time Control for Multi-Objective UAV Edge-Computing Scheduling [arXiv]
  19. QuanText: Protecting Dataset-Level Secrets in Textual Data Sharing [arXiv]
  20. Modeling the Developmental Shift in Telicity Acquisition [arXiv]
  21. The Attention Within: Consensus Dynamics in Selective State Space Models [arXiv]
  22. Three-dimensional simulations of accretion disks in pre-CE systems -- II. Accretion efficiency and angular momentum transport [arXiv]
  23. Does galaxy-scale compactness regulate nebular electron density? A cross-scale test with DESI [arXiv]
  24. Missing Bridges: Composition-Aware Active Imitation Learning [arXiv]
  25. A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality [arXiv]
  26. A Possible Hidden Hot Halo Component Revealed by Joint X-ray and Sunyaev--Zel'dovich Observations [arXiv]
  27. Newer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model Generations [arXiv]
  28. SG-Mamba: Sparse Graph-Guided Mamba for Audio-Visual Speech Enhancement [arXiv]
  29. Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX [arXiv]
  30. Improved lower bounds for decomposable randomized encoding [arXiv]
  31. Physics-Informed Neural Networks for Fast Multilayer Spectral Inversion of H alpha 6562.8 A and Ca II 8542.1 A Spectra [arXiv]
  32. Correlation-Guided Encoder Selection for Multi-Encoder Large Audio-Language Models [arXiv]
  33. Structural Inference under Hidden Agents [arXiv]
  34. Exact semantic readout from compressed vector representations [arXiv]
  35. Regional Explanations via Causal Sufficiency and Necessity [arXiv]
  36. An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks [arXiv]
  37. Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning [arXiv]
  38. The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction [arXiv]
  39. From a River in Gilead to the Inference Distributions of Large Language Models: Covert Dialect Bias and Linguistic Profiling at Scale [arXiv]
  40. Teaching AI, Robotics, & Community: A Hubs-Based K-12 Education Framework for Reaching Rural Schools [arXiv]
  41. vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes [arXiv]
  42. Beyond Embedding Transfer: Component Roles in Grokking Transfer and Stability [arXiv]
  43. Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition [arXiv]
  44. Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models [arXiv]
  45. FRB 20250607A: Weirder Than Fiction [arXiv]
  46. Mask 2D-3D: Adaptive Dual-Masked Autoencoder Network for Image-to-Point Cloud Registration [arXiv]
  47. FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels [arXiv]
  48. Agora: Git as Shared Memory for Collective AutoResearch [arXiv]
  49. When Is Graph Structure Worth Its Cost? The Case for Structure Pricing in Retrieval-Augmented Generation [arXiv]
  50. Beyond Pixel Similarity: Task-Aware Evaluation of GAN-Based Synthetic Sonar Data for Robotic Perception [arXiv]
  51. iMINDBench: iEEG Multi-Institution Neural Decoding Benchmark [arXiv]
  52. Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment [arXiv]
  53. FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detection [arXiv]
  54. A Comprehensive Review of Generative Physical Artificial Intelligence [arXiv]
  55. Token Latency Fairness: Performance Isolation for Multi-Tenant LLM Serving [arXiv]
  56. Preservation of Log-Concavity and Convergence of Wasserstein-Fisher-Rao Gradient Flows [arXiv]
  57. PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs [arXiv]
  58. "Your Robot Was Trained on a Lie": Collision Mesh Poisoning Attacks on Robotic Manipulation [arXiv]
  59. AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines [arXiv]
  60. Designing Agentic AI Workflow Portfolios under Imperfect Selection and Compute Cost [arXiv]

Listen

Everything the estate published on 2026-09-17, in the player. Playing from this page is how the edition learns whether anyone did.