INDEX
Every paper Pith has read and judged, in one searchable index.
-
cs.SE arXiv submitted 2026-07-31Typed server-side DSL replaces JavaScript for reactive web controls
Fernando Miguel Carvalho +4 · “BRHC: Backend-driven Reactive Hypermedia Controls with a Statically Typed Kotlin DSL”
2607.29338 -
cs.CV arXiv submitted 2026-07-31Transformer diffusion tops U-Net baselines for OCT and mask pairs
Fernando Garc\'ia-Torres +6 · “DualDiT: A Conditional Dual-Output Diffusion Transformer for Joint OCT Image and Segmentation Mask Generation”
2607.29337 -
cs.HC arXiv submitted 2026-07-31Rival-labeled AI persuades US users as well as an American one
Ningzhi Liu +2 · “The persuasive power of large language models does not depend on their perceived national origin”
2607.29334 -
cs.HC arXiv submitted 2026-07-31Nationality label doesn't change an AI chatbot's persuasive power
Ningzhi Liu +2 · “The persuasive power of large language models does not depend on their perceived national origin”
2607.29334 -
math.NA arXiv submitted 2026-07-31Multicontinuum upscaling gets a variational interface closure
Wing Tat Leung +1 · “I-MCHM: Interface Multicontinuum Homogenization for Multiscale Elliptic Problems”
2607.29325 -
cs.AI arXiv submitted 2026-07-31Action-aware distillation lifts unified GUI agent to 99.9% of teachers
Hang Yan +7 · “MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation”
2607.29320 -
cs.CL arXiv submitted 2026-07-31Ad auction picks the right moment in a chat
Yan Fang +7 · “LLM-OSDA: An Optimal-Stopping Dynamic Auction for Native Advertising in Multi-Turn LLM Conversations”
2608.00123 -
cs.AI arXiv submitted 2026-07-31Coding agents bank team know-how without being asked
Harsh Rao Dhanyamraju +1 · “Shared Organizational Memory for Enterprise Coding Agents: System Design and Deployment Snapshot”
2608.00122 -
cs.CV arXiv submitted 2026-07-31Three-expert gate lifts ambivalence detection to 0.7771
Wenzhuo Sun +5 · “CALM-AH: An ABAW11-Calibrated Multimodal Ensemble with Reliability-Gated Multi-Expert Consensus for Video-Level Ambivalence and Hesitancy Recognition”
2607.29310 -
math.AC arXiv submitted 2026-07-31Shrink resultant systems to Theta(s d^(n-1)) polynomials
M. Levent Do\u{g}an +2 · “Small Resultant Systems via Linear Combinations”
2607.29308 -
cs.NI arXiv submitted 2026-07-31On-switch GNNs diagnose optical faults in real time
Zhen Wei +6 · “RIGEL: Real-time Optical Anomaly Diagnosis with Stateful In-Network Inference based on Distributed On-switch GNNs”
2607.29306 -
eess.SY arXiv submitted 2026-07-31Optimized bus depot charging cuts electricity costs 25–60%
Fabio Widmer +3 · “Optimal Electric Bus Depot Charging: Cost Savings, Grid Limits, and Robustness Trade-Offs”
2607.29304 -
cs.DC arXiv submitted 2026-07-31Accuracy jumps from 67% to 96% for extended MPI checker
Yussur Mustafa Oraji +1 · “Allocation Tracking and Parameter Checking for Parallel Programming Models using Contracts”
2607.29303 -
cs.RO arXiv submitted 2026-07-31Learned simulator lifts robot success 20 points over real-only data
BWM Team · “BWM: A Low-Cost High-Fidelity World Simulator for Robot Learning”
2607.29302 -
cs.CY arXiv submitted 2026-07-31Course becomes a game world in working Unity–Blackboard build
Araz Yusubov +2 · “Hypergamigication Through Integrating Game Engines and Learning Management Systems: Ender's Game”
2607.29300 -
cs.LG arXiv submitted 2026-07-31Parallel HRL provably beats flat learning on sparse rewards
Anders Jonsson +3 · “Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification”
2607.29294 -
cs.LG arXiv submitted 2026-07-31Space-time graph nets keep fault location above 81% F1
Burak Karabulut +4 · “Assessing the Generalization of Graph Neural Networks for Fault Location Across Increasing Distributed Energy Resource Penetration Levels”
2607.29293 -
cs.SC arXiv submitted 2026-07-31All ten 'unsatisfiable' matrix-multiplication formulas are satisfiable
Nick Palladinos · “SAT Certificates for the Matrix-Multiplication Challenges over F2: All Ten `Expected-UNSAT` Instances Are Satisfiable, and a Type-3-Free Rank-23 Scheme”
2607.29291 -
cs.IT arXiv submitted 2026-07-31Passive IoT overlay shifts optimal Wi-Fi sounding interval
Muhan Zhang +6 · “Data-Driven Batteryless Channel Sounding for Wi-Fi 8-Inspired Downlink MU-MIMO”
2607.29288 -
cs.CL arXiv submitted 2026-07-3114B translator out-scores reasoning giants in fewer tokens
Yongshi Ye +4 · “Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation”
2607.29287 -
cs.RO arXiv submitted 2026-07-31Boundary-routed action chunks: 6/10 vs 3/10 success
Jiahao Liu +3 · “TRACT: Temporally Routed Action Chunks with Chronological Phase Authority for Contact-Rich Manipulation”
2607.29285 -
cs.CV arXiv submitted 2026-07-31Sparse 4D video renders sharper with motion-aware view selection
Takashi Otonari +1 · “FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement”
2607.29284 -
cs.AR arXiv submitted 2026-07-31Curating 80% of noisy RTL data beats using all of it
Siyang Cai +6 · “RTLCurator: Label-Efficient Data Curation for RTL Generation”
2607.29283 -
cs.NI arXiv submitted 2026-07-31Uplink slice promises need radio-side enforcement
Arman Divband +2 · “METIS: A Declarative Slice Orchestrator for Application-Centric 5G/6G Networks”
2607.29282 -
cs.SD arXiv submitted 2026-07-31ParaASR emits 5 verified transcript tokens per LLM step
Qingjian Lin +16 · “ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition”
2607.29279 -
cs.CV arXiv submitted 2026-07-31Training-free remote sensing segmentation hits 36.37 mIoU
Xueting Bai +1 · “Training-Free Entity-Level Few-Shot Segmentation of Remote Sensing Images with Advection Refinement”
2607.29278 -
cs.IR arXiv submitted 2026-07-31Models agree 2.3x more with each other than with readers
Kazuki Nakayashiki +1 · “Language Models Agree With Each Other, Not With Readers”
2607.29274 -
cs.DM arXiv submitted 2026-07-31Temporal role colouring is NP-complete
Jessica Enright +3 · “Temporal Role Colouring”
2607.29272 -
cs.RO arXiv submitted 2026-07-31All 15 contact-rich demos keep working with gentler forces
Liu Jiahao +3 · “MDIR: A Task-Manifold Impedance Retargeting Method for Contact-Rich Teleoperation”
2607.29271 -
math.NA arXiv submitted 2026-07-31Newton–Schulz iteration provably finds split-quaternion pseudoinverse
Salman Ahmadi-Asl +2 · “Iterative Methods for Computing the Moore--Penrose Inverse of Split-Quaternion Matrices with Applications”
2607.29270 -
cs.CV arXiv submitted 2026-07-31Tumor-segmentation AI works even where no dataset or GPU exists
Maximo Rodriguez-Herrero +5 · “OsteoCAD: A Human-in-the-Loop Cloud-Edge Framework for Bone Tumor Segmentation”
2607.29266 -
cs.LG arXiv submitted 2026-07-31AI pipeline hits polyimide Tg prediction R²=0.93
Junquan Hu +6 · “UniPolymer: A Unified Framework for Property Prediction, Structure Recommendation, and Evaluation in Polyimide Design”
2607.29256 -
cs.DM arXiv submitted 2026-07-31New theorems settle when juggling extensions stay valid
Hugo Parada (SPHINX +1 · “About two results for new valid juggling sequences”
2607.29255 -
cs.CV arXiv submitted 2026-07-31Depth cues halve dense-city building-count errors
Saleh Sakib Ahmed +1 · “Counting the Cost of War Under Satellite Embargo: Zero-Shot Estimation of Impacted Infrastructure”
2608.00119 -
cs.AI arXiv submitted 2026-07-31Tool specs, not tools, break LLM agent safety
Minghui Pan +4 · “Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents”
2607.29254 -
cs.CR arXiv submitted 2026-07-3199.99% accuracy: a small TCN catches health-IoT DDoS attacks
Mirza Akhi · “Deep Learning for Cyber Threat Detection and Mitigation in Healthcare-IoT”
2608.00118 -
physics.med-ph arXiv submitted 2026-07-311,764 annotated CBCT slices become a public image-quality benchmark
Sepideh Hatamikia +16 · “CBCT-IQ: A Publicly Available Annotated Cone-Beam CT Dataset for Image Quality Assessment and Benchmarking”
2607.29253 -
cs.CL arXiv submitted 2026-07-31IRT and a measurability filter cut rubric banks from 131 to 49
Mengting Chen +7 · “CalibratedRubric: Task-Adaptive Rubric Banks for Open-Ended LLM Evaluation”
2607.29252 -
cs.CL arXiv submitted 2026-07-31Stepwise data generation lifts small models past 32B on tool use
Goutham Ramakrishnan +1 · “Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation”
2607.29250 -
cs.SE arXiv submitted 2026-07-31Mutation consistency reveals silent transpiler faults
Enea Raffaele Ilario Papaleo +2 · “Metamorphic Testing of Transpilers via Mutation Consistency of Programs”
2607.29247 -
cs.AI arXiv submitted 2026-07-31Policy-space mixing beats reward mixing for multi-goal LLMs
Ruiming Liang +8 · “Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL”
2607.29246 -
stat.ML arXiv submitted 2026-07-31Expected improvement is minimax-optimal
Emmanuel Vazquez +1 · “Simple-regret rates and minimax optimality of fixed-prior expected improvement in Mat\'ern and squared-exponential RKHSs”
2607.29245 -
cs.CR arXiv submitted 2026-07-31JUNO's vector votes drop ACS messages to O(n^2)
Liangrong Zhao +3 · “JUNO: Aggregated Vector Consensus for Optimal Asynchronous Common Subset”
2607.29244 -
cs.CV arXiv submitted 2026-07-31AI tool sizes aortic valves in minutes
Alessandra Zerillo +6 · “TAVI-TEC: An AI-Based Tool for Procedural Planning of Transcatheter Aortic Valve Implantation”
2607.29243 -
cs.IR arXiv submitted 2026-07-31Bandit routing steadies LLM-driven recommender tuning
Haoran Ling +7 · “RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems”
2607.29241 -
cs.CV arXiv submitted 2026-07-31Subtracting no-image bias lifts counterfactual accuracy 7.8 points
Kesheng Chen +2 · “When Model Priors Conflict with Visual Evidence: Mitigating Commonsense-Driven Hallucinations by Selective Prior Calibration”
2607.29240 -
cs.CL arXiv submitted 2026-07-31Tiny LoRA models match 7B on user-style rewriting
Antorweep Chakravorty · “Small Is Enough: Per-User Style Rewriting of AI-Edited Text via LoRA Adapters”
2607.29238 -
cs.CV arXiv submitted 2026-07-31Zero-parameter scene flow ranks second and holds long range
Minh-Quan Dao +3 · “CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation”
2607.29237 -
math.CO arXiv submitted 2026-07-31One search counts every triangle-maximal pseudoline arrangement to n=27
Roman Parpalak +1 · “Enumeration and Classification of Triangle-Maximal Pseudoline Arrangements”
2607.29236 -
cs.RO arXiv submitted 2026-07-31Training-free feedback lifts robot success by 3 points
Peize Li +5 · “FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution”
2607.29235