parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning

• URL: http://arxiv.org/abs/2605.15509v1
• Date: Fri, 15 May 2026 01:06:16 GMT
• Title: parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning
• Abstract summary: We release ParallelCBF v0.1.0 under Apache2.0 with a four-layer composable API, a CPU PyTorch reference implementation of a dual-barrier (squared / linear-predictive) CBF.<n>We report a representative end-to-end pipeline execution in which the framework's auditability layer halted a downstream training stage that did not meet pre-registered convergence criteria.
• Score: 0.45470638320073126
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Isaac Lab provides massive parallel UAV simulation, OmniSafe and safe-control-gym provide constrained-RL benchmarks, and CBFKit provides control-barrier-function synthesis tooling, no existing framework unifies these capabilities for end-to-end safety-constrained training. ParallelCBF is the first framework to unify (i)~tensor-parallel UAV environments, (ii)~hard-gate CBF safety filters, (iii)~sharded BC-to-RL pipelines, and (iv)~first-class operational auditability -- pre-registration, watchdog registries, failure forensics, and dataset audits as composable APIs rather than user-implemented scripts. We release ParallelCBF v0.1.0 under Apache~2.0 with a four-layer composable API, a CPU PyTorch reference implementation of a dual-barrier (squared / linear-predictive) CBF, property-based safety invariance tests across vectorized batch sizes that complete in 1.67~s for the full 39-test suite, and a 31{,}415-episode behavior-cloning collection campaign whose curriculum mix, per-bucket yields, and dataset SHA-256 are auditable through the framework's own \texttt{ops} primitives. We report a representative end-to-end pipeline execution in which the framework's auditability layer halted a downstream training stage that did not meet pre-registered convergence criteria, preventing silent propagation of a degraded checkpoint -- an architectural property we argue is necessary, not merely useful, for reproducible empirical robotics research. The framework is installable via \texttt{pip install parallelcbf}; source and release artifacts are available at https://github.com/xiaoyang-123-cell/ParallelCBF.

Related papers

• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• CHAINTRIX: A multi-pipeline LLM-augmented framework for automated smart-contract security auditing [3.8615905456206256]
  Chaintrix is an end-to-end auditing framework for smart-contract exploits.<n>It detects 86 of 120 high-severity vulnerabilities, with 25 audits scoring 100% recall.
  arXiv  Detail & Related papers  (2026-05-10T06:02:22Z)
• Enforcing Attestable Workflows across Untrusted Networks [0.0]
  We propose codename, an architecture federating Trusted Execution Environments via a split Trusted Computing Base design.<n>codename achieves native-speed encrypted routing by anchoring cryptographic enforcement in the kernel.<n>On distributed pipelines, codename incurs just a $6.1%$ execution penalty over plaintext baselines, bypassing the $62%$ penalty of user-space counterparts.
  arXiv  Detail & Related papers  (2026-05-10T03:45:22Z)
• ClawGym: A Scalable Framework for Building Effective Claw Agents [47.47444724291439]
  We present ClawGym, a scalable framework that supports the full lifecycle of Claw-style personal agent development.<n>ClawGym-SynData is a dataset of 13.5K filtered tasks synthesized from persona-driven intents and skill-grounded operations.<n>We then train a family of capable Claw-style models, termed ClawGym-Agents, through supervised fine-tuning on black-box rollout trajectories.<n>We further construct ClawGym-Bench, a benchmark of 200 instances through automated filtering and human-LLM review.
  arXiv  Detail & Related papers  (2026-04-29T17:12:22Z)
• LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learning [1.2599533416395765]
  Three-dimensional (3D) point cloud analysis has become central to applications ranging from autonomous driving and robotics to forestry and ecological monitoring.<n>lib is a unified, PyTorch library that integrates over 55 model configurations covering 29 supervised architectures, seven SSL pre-training methods, and five PEFT strategies.<n>lib provides standardised training runners, cross-validation with stratified $K$-fold splitting, automated/CSV table generation, built-in Friedman/Nemenyi statistical testing with critical-difference diagrams for rigorous multi-model comparison, and a comprehensive test suite with 2,200+ automated tests
  arXiv  Detail & Related papers  (2026-04-12T19:10:12Z)
• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control [61.155940786140455]
  Reinforcement learning (RL) has shown promising results in active flow control (AFC)<n>Current AFC benchmarks rely on external computational fluid dynamics (CFD) solvers, are not fully differentiable, and provide limited 3D and multi-agent support.<n>We introduce FluidGym, the first standalone, fully differentiable benchmark suite for RL in AFC.
  arXiv  Detail & Related papers  (2026-01-21T14:13:44Z)
• Exposing Hidden Interfaces: LLM-Guided Type Inference for Reverse Engineering macOS Private Frameworks [7.370020034607549]
  MOTIF is an agentic framework that integrates tool-augmented analysis with a large language model specialized for Objective-C type inference.<n>By transforming binaries into analyzable interfaces, MOTIF establishes a scalable foundation for systematic auditing of runtime internals.
  arXiv  Detail & Related papers  (2026-01-04T21:44:55Z)
• Boundary-to-Region Supervision for Offline Safe Reinforcement Learning [56.150983204962735]
  Boundary-to-Region (B2R) is a framework that enables asymmetric conditioning through cost signal realignment.<n>B2R redefines CTG as a boundary constraint under a fixed safety budget, unifying the cost distribution of all feasible trajectories.<n> Experimental results show that B2R satisfies safety constraints in 35 out of 38 safety-critical tasks.
  arXiv  Detail & Related papers  (2025-09-30T03:38:20Z)
• SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functions [0.0]
  We present SafeFlowMatcher, a planning framework that couples flow matching (FM) with control barrier functions (CBFs) to achieve both real-time efficiency and certified safety.<n>We prove a barrier certificate for the resulting flow system, establishing forward invariance of a robust safe set and finite-time convergence to the safe set.<n>Across maze navigation and benchmarks, SafeFlowMatcher attains faster, smoother, and safer paths than diffusion- and FM-based baselines.
  arXiv  Detail & Related papers  (2025-09-29T03:33:33Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• B-Side: Binary-Level Static System Call Identification [1.6050948947693462]
  We present B-Side, a static binary analysis tool able to identify a superset of the system calls that an x86-64 static/dynamic executable may invoke at runtime. B-Side assumes no access to program/libraries sources, and shows a good degree of precision by leveraging symbolic execution.
  arXiv  Detail & Related papers  (2024-10-23T17:26:52Z)
• Semi-DETR: Semi-Supervised Object Detection with Detection Transformers [105.45018934087076]
  We analyze the DETR-based framework on semi-supervised object detection (SSOD) We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector. Our method outperforms all state-of-the-art methods by clear margins.
  arXiv  Detail & Related papers  (2023-07-16T16:32:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.