Thursday 13 August

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.

7974 papers, three ways

Where today's batch landed

The index

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

1. Hamilton-Zero: A Neural Tensor-Network Foundation Model for Ground States of Arbitrary Quadratic Qubit Hamiltonians [arXiv]
2. LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence [arXiv]
3. Persistent Recursive Worlds Enable Autonomous Software Evolution [arXiv]
4. Kratos-linerad: GPU-accelerated Monte Carlo radiative transfer of lines with efficient imaging [arXiv]
5. DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models [arXiv]
6. OEIS Open: How many conjectures can language models turn into theorems? [arXiv]
7. Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning [arXiv]
8. Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations [arXiv]
9. Keep the Future, Drop the Rollout: RIFT for World Action Models [arXiv]
10. Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning [arXiv]
11. Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation [arXiv]
12. Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models [arXiv]
13. Automated binary classification of hazelnut X-ray images: A deep-learning benchmark for quality assessment [arXiv]
14. Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library [arXiv]
15. ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents [arXiv]
16. CoQui: A Coordinate-Conditioned Quantum Implicit Generative Adversarial Network for End-to-End Image Generation [arXiv]
17. Disentangling the Expressivity of RoPE [arXiv]
18. Classifying Quasar Types Without a Spectrum [arXiv]
19. Distillation of Foundation Models for Time-dependent PDEs [arXiv]
20. Identification of a Large-Scale Diffuse Gamma-Ray Structure in the Southern Galactic Hemisphere [arXiv]
21. Graph-Structured Rubrics: Compiling Rubrics into Typed Evaluation Graphs for LLM Judges [arXiv]
22. HSTGFormer: Hyper Spatial-Temporal Graph Transformer for 3D Human Pose Estimation [arXiv]
23. Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deployment [arXiv]
24. High-energy neutrino signatures of embedded GRB jets in AGN disks: a dynamic jet-propagation framework [arXiv]
25. Evidence for the First Globular Cluster Stellar Stream beyond the Milky Way [arXiv]
26. AVA-Encoder: Towards Agent-Native Video Representation Learning [arXiv]
27. Telemetry and Concealment in Self-Adapting Generative AI: Logging Architecture, Adversarial Model Hiding, and the Limits of Detection [arXiv]
28. A Single Atom in Front of a Mirror is a Universal Reservoir Computer [arXiv]
29. Recovering Wasted Compute in Autoresearch Agents [arXiv]
30. Causality Sum Rules in Conventional Scattering Matrices [arXiv]
31. RAISE: Diagnosing Acquisition Collapse in Costly LLM Signals [arXiv]
32. Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging [arXiv]
33. A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes [arXiv]
34. ImpactHO: Importance-Aware KV Cache Transfer for Multi-User Edge LLM Handover [arXiv]
35. MARCO: Click-Intent Decomposition for Calibrated Ads Conversion Prediction [arXiv]
36. DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation [arXiv]
37. Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts [arXiv]
38. Pair-Centric Graph Rewiring for Over-Squashing via Optimal Transport-Guided Communication Alignment [arXiv]
39. ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions [arXiv]
40. ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes [arXiv]
41. Most biomedical publications show signs of LLM-assisted writing [arXiv]
42. Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence [arXiv]
43. SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation [arXiv]
44. ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation [arXiv]
45. Hypothesis Frontier: Verifier Guided LLM and Symbolic Search for First-Order Induction [arXiv]
46. Diffract: Spectral View of LLM Domain Adaptation [arXiv]
47. Order Matters: LVLMs as Judges for Temporal Reasoning in Image Sequences [arXiv]
48. Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation [arXiv]
49. Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers [arXiv]
50. Gromov-Wasserstein Quantization and Clustering: Structure, Rates, and Algorithms [arXiv]
51. DEFT: Data-Efficient Frequency-domain Top-k Sampling via Inverse Discrete Fourier Transform for Spatiotemporal Dynamical Systems Modeling [arXiv]
52. Agent Safety Should Be a Runtime Contract [arXiv]
53. Formation of multiple dust rings and gaps in protoplanetary discs by a single migrating planet. A parameter study in locally isothermal discs [arXiv]
54. Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations [arXiv]
55. Dual-Domain Cross-Modal Decoding for Clinical Text-Guided Medical Image Segmentation [arXiv]
56. Governing Agentic AI in FinTech [arXiv]
57. Three Tokens Force Exponential Feature Rank in Nonnegative Kernel Attention [arXiv]
58. TangPoetryBench: A Multi-Dimensional Benchmark and Rubric-Conditioned Evaluator for Poetry-to-Image Generation [arXiv]
59. Torsional pseudo-inflation beyond Einstein-Cartan [arXiv]
60. PAC-Bayes Beyond Parameter Space: Behavioral Equivalence, Z-Information, and Exact Complexity Decomposition [arXiv]