Pith. sign in

INDEX

Every paper Pith has read and judged, in one searchable index.

90,023 reviewed papers in cs · newest first · page 9

Pith rank means recent reader upvotes with each upvote's ranking weight halved after 24 hours. The archive itself is sorted by arXiv submission date.

  1. cs.RO arXiv submitted 2026-07-31
    Safety filter inside denoising keeps robot actions provably safe

    Kasra Sinaei +2 · “Safe Vision Language Action Models via Barrier Enhanced Flow Matching”

    2607.29569
  2. cs.CV arXiv submitted 2026-07-31
    Gated phase-difference fusion cuts liver lesion boundary errors by 15%

    Yu-Pu Hsu +2 · “DynoDINO: Harnessing Dynamic Latent Information from DINO Features for Multi-Phase Medical Image Segmentation”

    2607.29568
  3. cs.RO arXiv submitted 2026-07-31
    Robot grasps transparent labware with zero spillage at 0.5 m/s

    Hailing Hu +5 · “TransGraspNet: Physically and Geometrically Consistent Manipulation of Transparent Labware”

    2607.29567
  4. math.OC arXiv submitted 2026-07-31
    Node-wise incentives force cooperation on multilayer networks

    Rio Aurachman +1 · “Node-Wise Dynamic Optimal Control for Evolutionary Games on General Multilayer Networks”

    2607.29563
  5. cs.LG arXiv submitted 2026-07-31
    One symbolic equation cuts long-orbit error 27-fold

    Boxiao Wang +6 · “MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models”

    2607.29561
  6. cs.AI arXiv submitted 2026-07-31
    No reward functions: an agent learns to balance competing goals

    Manith Adikari +3 · “LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback”

    2607.29559
  7. cs.SE arXiv submitted 2026-07-31
    Behavior broke as accuracy rose: new tool catches NLP regressions

    Shazzad Hossain (University of Dhaka) +2 · “Alteron: A Tool for Behavioral Regression Testing Across NLP Classifier Versions”

    2607.29557
  8. cs.LG arXiv submitted 2026-07-31
    Adding one vertex can raise pyramidal width by 41 percent

    Jinze Zhao · “Pyramidal Width Can Increase Under Vertex Insertion”

    2607.29555
  9. cs.AI arXiv submitted 2026-07-31
    Metric files give ontology updates a context boost

    Hussain Hussain +3 · “COntExt: Towards Context-Aware Ontology Extension from Operational Metrics”

    2607.29553
  10. cs.LG arXiv submitted 2026-07-31
    Sampling extracts one in six document identifiers

    Victor Maricato · “Leak It: A Probabilistic Approach to Training-Data Extraction from Black-Box Language Models”

    2608.00144
  11. cs.SE arXiv submitted 2026-07-31
    Nine pattern symbols make DCR graphs feel clearer

    Amine Abbad-Andaloussi +4 · “Improving the Understandability of Conceptual Models via Abstract Notation Engineering”

    2607.29552
  12. cs.CR arXiv submitted 2026-07-31
    The two-part test for whether disruption improves a system

    Stephen Flowerday +2 · “Beyond Resilience: Antifragility in Critical Infrastructure Cybersecurity”

    2607.29550
  13. cs.AI arXiv submitted 2026-07-31
    Tool-flow verification lifts LLM math accuracy by 8.3 points

    Rui Zou +3 · “AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction”

    2607.29549
  14. cs.CV arXiv submitted 2026-07-31
    Dynamic layer routing lifts video generation scores by 0.15–0.34

    Chong Gao +7 · “MoRoute: Dynamic Routing for In-Context Multimodal Video Generation”

    2607.29545
  15. eess.SY arXiv submitted 2026-07-31
    Hurricane repair scheduler cuts restoration makespan by half

    Hooman Torkaman +2 · “Quantum Inspired QUBO Assisted ALNS for Reliability Driven Hurricane Restoration of Distribution Networks”

    2607.29544
  16. cs.CV arXiv submitted 2026-07-31
    Spectral subtraction catches fake MRI scans

    Riccardo Raciti +4 · “The K-Space Signature: Frequency-Domain Representation Learning for Medical Deepfake Detection”

    2607.29541
  17. cs.CV arXiv submitted 2026-07-31
    Frequency-domain fingerprint spots synthetic MRI at 99% accuracy

    Riccardo Raciti +4 · “The K-Space Signature: Frequency-Domain Representation Learning for Medical Deepfake Detection”

    2607.29541
  18. cs.CY arXiv submitted 2026-07-31
    No single U.S

    Emma Lurie +4 · “Triangulating Across U.S. Federal AI Transparency Regimes”

    2607.29540
  19. cs.CL arXiv submitted 2026-07-31
    AI text detectors fall to 15% recall on AI-polished human drafts

    Gaetano Perrone +1 · “ARB: A Matched Authorship-Rewriting Benchmark Dataset for AI-Text Detector Evaluation”

    2607.29539
  20. cs.CR arXiv submitted 2026-07-31
    Five predicate categories match nine for attack planning

    Ramya Varunsegar · “Symbolic Attack Chain Generation from Atomic Red Team Techniques: An Empirical Study of Predicate Representation Granularity”

    2608.00143
  21. cs.CV arXiv submitted 2026-07-31
    New synthetic-defect generator tops pixel-level anomaly localization

    Jinyi Xu +5 · “OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation”

    2607.29533
  22. cs.CV arXiv submitted 2026-07-31
    Depression model adapts to 7 new brain-scan sites at 73.6% accuracy

    Zhanpeng Zheng +8 · “Multi-Source Multi-View Graph Domain Adaptation with Hyperbolic Residual Encoding for Cross-Site MDD Identification from rs-fMRI”

    2607.29531
  23. cs.LG arXiv submitted 2026-07-31
    Audio-only pipeline recovers known Alzheimer's language markers

    Ranveer Singh +8 · “A Neurosymbolic Approach for Explainable Early Diagnosis of Alzheimer's Disease”

    2607.29530
  24. cs.SE arXiv submitted 2026-07-31
    Pre-code responsibility IDs make LLM repairs bounded and auditable

    Kangjie Huang +1 · “AuditCoder: Responsibility-Preserving Task Graphs for Auditable Code Generation and Bounded Repair”

    2607.29529
  25. cs.LG arXiv submitted 2026-07-31
    One model learns 1,024 variables across two data geometries

    Carlos Rodriguez-Pardo +1 · “TerraNova: A Foundation Model for the Anthropocene”

    2607.29527
  26. math.OC arXiv submitted 2026-07-31
    Denoisers must match the physics for PnP recovery to work

    Tobias Wolf +3 · “Physics Matters in PnP: Recovery Guarantees with the MMSE and NN Denoisers”

    2607.29525
  27. cs.NI arXiv submitted 2026-07-31
    Lighthouse pulses tune crystal-free radios to BLE

    Cheng Wang +5 · “LightCal: Lightweight Optical-Pulse Bootstrap Calibration for Crystal-Free BLE Radios”

    2608.00141
  28. cs.SE arXiv submitted 2026-07-31
    Students outsource the struggle to LLMs and lose the skill

    Enne Rebeca Silva de Freitas +2 · “Students' Practices and Skills in the LLM-Era: "You Can't Outsource the Struggle and Still Get the Skill"”

    2607.29519
  29. cs.RO arXiv submitted 2026-07-31
    One slider controls how aggressively an autonomous vehicle drives

    Zihao Liu +3 · “STAGE: STyle-controllable Action GEneration for personalized autonomous driving”

    2607.29517
  30. cs.SE arXiv submitted 2026-07-31
    Surfacing drift scores cuts AI-code misalignment by 5.76 points

    Chandra Maddila +6 · “From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale”

    2607.29516
  31. cs.RO arXiv submitted 2026-07-31
    Build robot corridors directly from free space

    Haoze Dong +3 · “Homotopy-Aware Corridor Generation without Predefined Reference Paths”

    2607.29513
  32. cond-mat.mtrl-sci arXiv submitted 2026-07-31
    Formation energy transfers to high-entropy oxides

    Panupol Untarabut +6 · “Ordered-to-disordered transfer learning with graph neural networks for formation-energy and HOMO-LUMO gap prediction in high-entropy perovskite oxides”

    2607.29510
  33. cs.CV arXiv submitted 2026-07-31
    Gallbladder-trained model hits 62.4% dice on rectal-surgery images

    Priya Tomar +3 · “Leveraging Transfer Learning with Class-Specific Decoders for Laparoscopic Segmentation”

    2607.29509
  34. cs.LG arXiv submitted 2026-07-31
    High-entropy models keep 95% of old task

    Xiaotian Zhang +4 · “The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting”

    2607.29503
  35. cs.RO arXiv submitted 2026-07-31
    Tune a few parameters, cut cable-robot error 64%

    Dipankar Bhattacharya +5 · “Tri-Space Operational Control of Redundant Multilink and Hybrid Cable-Driven Parallel Robots Using an Iterative-Learning based Reactive Approach”

    2607.29500
  36. cs.LG arXiv submitted 2026-07-31
    Two pop-enabled transcripts make Transformers Turing-complete

    Sergey Salishev · “Transcript-Managed Transformers: Monotone Multi-Agent Collapse and Universality with Two Pop-Enabled Transcripts”

    2607.29496
  37. math.PR arXiv submitted 2026-07-31
    Poisson-tree mixing is near-linear

    Zongchen Chen +5 · “Fast Mixing for Low-Temperature Potts Models via Poisson Trees”

    2607.29495
  38. cs.LG arXiv submitted 2026-07-31
    Adaptive rollout schedule cuts distillation time up to 71%

    Qian Tan +4 · “Adaptive FastOPD: Progress-Aware Rollout Horizon Expansion for Efficient On-Policy Distillation”

    2607.29494
  39. cs.HC arXiv submitted 2026-07-31
    Adding gaze variability lifts MCI discrimination AUC to 0.78

    Takeru Mukunoki +6 · “Exploratory Integration of EEG Spectral Features and Gaze Variability for Mild Cognitive Impairment Discrimination”

    2607.29493
  40. math.HO arXiv submitted 2026-07-31
    Banaszczyk's theorem yields low-discrepancy colorings

    Nikhil Bansal +1 · “Discrepancy Theory: An Algorithmic and Geometric Perspective”

    2608.00140
  41. cs.LG arXiv submitted 2026-07-31
    A dreamed world model cuts real VQE calls up to 10.6x

    Jiayang Niu +6 · “DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture Search”

    2607.29491
  42. cs.CL arXiv submitted 2026-07-31
    Context, not training mix, decides LLM causal direction

    Xining Xun · “Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?”

    2607.29484
  43. cs.RO arXiv submitted 2026-07-31
    Robot policies start from past states

    Dylan Miller +1 · “Temporal Policy: History-Initialized Action Generation for Robotic Learning from Demonstration”

    2607.29482
  44. eess.SY arXiv submitted 2026-07-31
    Plant-free shaping filter makes data-driven tuning exact

    Yusuke Fujimoto · “Optimal shaping filter design for data-driven feedforward controller tuning”

    2607.29480
  45. cs.LG arXiv submitted 2026-07-31
    Verify-then-refine loop lifts exact molecule matches

    Qian Tan +5 · “MolGVR: A Chemistry-Grounded Framework for Text-to-Molecule Generation”

    2607.29479
  46. cs.DC arXiv submitted 2026-07-31
    Global stop signal cuts distributed betweenness error to zero

    Siamak Abdi +2 · “System-Wide Termination in Distributed Betweenness Centrality Computation”

    2607.29474
  47. cs.CV arXiv submitted 2026-07-31
    Better decoders beat a heavier baseline for affordance segmentation

    Simone Lugani +3 · “Lightweight Neural Networks for Affordance Segmentation: Enhancement of the Decoder Module”

    2607.29473
  48. math.NA arXiv submitted 2026-07-31
    Martingale PDEs solved by iterated least-squares regression

    Tiejun Li +2 · “iSMART: An Iterative Sampling-and-Regression Technique for Solving Martingale-Based PDEs”

    2607.29470
  49. cs.AI arXiv submitted 2026-07-31
    Self-play agent that remembers its failures gains 1.2–3.2 points

    Zenghuang Fu +8 · “Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember”

    2607.29468
  50. eess.IV arXiv submitted 2026-07-31
    Underwater images come clean with teacher-student prior learning

    Yifan Chen +4 · “RPL-UIE: Reliable Prior Learning for Underwater Image Enhancement”

    2608.00137