Friday 14 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.

406 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. A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family [arXiv]
2. CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility [arXiv]
3. Homomorphic Aggregation of Continuous-Variable GKP States [arXiv]
4. Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing [arXiv]
5. Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples [arXiv]
6. Demand Transfer Estimation at Scale via Restricted Logit Modeling [arXiv]
7. CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation [arXiv]
8. X-ray signals converted from high-frequency gravitational waves emitted by spinning light primordial black hole dark matter [arXiv]
9. Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses [arXiv]
10. Foundations of MT-PDCL: Measure-Theoretic Probabilistic Definite Clause Logic [arXiv]
11. From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion [arXiv]
12. EEG-PRIME: Prototype-Aligned Representation Learning with Multi-Level Conditioning for EEG Decoding [arXiv]
13. FOSSIL's preliminary thermal architecture [arXiv]
14. TANGCO: Learning Topology-Aware Capacity Allocation for Overload-driven Cascading Failures [arXiv]
15. Optical development of the BISOU breadboard [arXiv]
16. Localize, Then Reason: Visual Latent Structural Reasoning for Molecular Properties and Edits [arXiv]
17. Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services [arXiv]
18. Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws [arXiv]
19. Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation [arXiv]
20. LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning [arXiv]
21. Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development [arXiv]
22. ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models [arXiv]
23. Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling [arXiv]
24. Synthetic Persona Pretraining: Alignment from Token Zero [arXiv]
25. AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1) [arXiv]
26. Equivariant learning of a transferable three-dimensional classical density functional [arXiv]
27. HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference [arXiv]
28. Non-Degenerate Risk Certification for Automated Security Decisions: A Decision-Contract Theory with ATT&CK-Aligned Triage as a Worked Instance [arXiv]
29. Exemplar-based objective classification of gust-induced loads across multiple flight conditions [arXiv]
30. Singlet-Doublet fermion origin of dark matter, neutrino mass and inverse first-order electroweak phase transition [arXiv]
31. epsilon-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution [arXiv]
32. Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces [arXiv]
33. Interpretable Causal Discovery via Causal-Effect Constraints [arXiv]
34. Training Under Challenge: Executable Certificates and Challenge-Closed Optimality for Neural Networks [arXiv]
35. Effects of Quantum Spin-Connection Foam in the Solar System, Galaxies, and the Universe [arXiv]
36. RealmEye: Virtual Machine Introspection for Arm CCA Realm VMs [arXiv]
37. History-informed Lagrangian Neural Networks [arXiv]
38. Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation [arXiv]
39. CAPRI: Contract-Aware Proof Repair for Isabelle [arXiv]
40. BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving [arXiv]
41. Federated Compositional Muon Optimizer for Matrix-Wise Models [arXiv]
42. Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness [arXiv]
43. Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review [arXiv]
44. SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization [arXiv]
45. InterSAGE: The Secure and Verifiable Interoperability Protocol for An Internet of Agents [arXiv]
46. TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes [arXiv]
47. GEM: A Generative Embedding Model Bridging Reasoning and Retrieval [arXiv]
48. Does Fixing Break Security? An Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-as-Code Repair [arXiv]
49. On the Expressive Power of Transformers [arXiv]
50. High-resolution Calibrated Probabilistic Hourly Precipitation from a Deterministic Forecast [arXiv]
51. Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks [arXiv]
52. ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval [arXiv]
53. A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Settings [arXiv]
54. Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents [arXiv]
55. ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs [arXiv]
56. PIPES: Securing Agent Perception with Provenance and Priors [arXiv]
57. Fine-tuned Normalizing Flows for ALICE Zero Degree Calorimeter Fast Simulation [arXiv]
58. AQuA: Recursively Self-Improving Quantitative Trading Research Agents [arXiv]
59. Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval [arXiv]
60. Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories [arXiv]

Listen

Everything the estate published on 2026-08-14, in the player. Playing from this page is how the edition learns whether anyone did.

• Spectroscopic Binary Detection as Agent-Callable Tools: Detecting 40,000+ Main-Sequence Binary Candidates from SDSS DR19 APOGEE Spectra