{"total":14,"items":[{"citing_arxiv_id":"2606.19532","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Vancomycert: A Certified Neuro-Symbolic Drug Delivery System (Case Study)","primary_cat":"cs.LO","submitted_at":"2026-06-17T19:26:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Case study verifying a neural network drug-dosing controller for infinite-horizon safety using Rocq and the Vehicle theorem prover.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20698","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model","primary_cat":"cs.RO","submitted_at":"2026-06-15T08:58:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SafeDojo is a new world model-based safe RL framework for VLA that outperforms baselines on SafeLIBERO and real robot tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10288","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds","primary_cat":"cs.RO","submitted_at":"2026-06-09T01:21:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MARCH combines simplified-model trajectory generation with CLF-guided teacher RL and vision-policy distillation to enable stable humanoid locomotion over sparse terrain with better sample efficiency than pure model-free methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09749","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models","primary_cat":"cs.RO","submitted_at":"2026-06-08T17:11:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Internal attention heads in VLA policies localize targets for a CBF safety filter that enables real-time collision avoidance with dynamic obstacles and outperforms init-time oracle identification by 43% on average.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09416","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer","primary_cat":"cs.RO","submitted_at":"2026-06-08T12:29:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Robot middleware is the harness for Physical AI and should implement Projection, Isolation, and Transfer to enforce AI model outputs across control, computation, and communication.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07193","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filtering","primary_cat":"cs.RO","submitted_at":"2026-06-05T11:59:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A post-hoc predictive safety filter adjusts RL policy contact locations for quadruped robots via sampling-based optimization on a full-physics model, reducing safety violations in cluttered environments with minimal performance deviation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00374","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Constrained Whole-Body Tracking for Humanoid Robots","primary_cat":"cs.RO","submitted_at":"2026-05-29T21:33:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ConstrainedMimic integrates operational space control and control barrier functions into RL tracking policies to enforce arbitrary runtime constraints on humanoid kinematics and dynamics while preserving contact modes and tracking goals.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00090","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems","primary_cat":"cs.RO","submitted_at":"2026-05-23T16:48:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A literature review that defines silent physical-action failures in Physical AI and identifies the lack of complete runtime authorization boundaries across surveyed technical streams.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00089","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Can Predicted Dynamics Exist in the Physical World?","primary_cat":"cs.RO","submitted_at":"2026-05-23T16:28:59+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19009","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Adversarial Stress Testing of SPARK Humanoid Safety Filters","primary_cat":"cs.RO","submitted_at":"2026-05-18T18:32:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Replicates SPARK humanoid safety filters and stress-tests them under crowding, noise, and delays, showing trade-offs in goal tracking versus collision reduction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16660","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Trajectory-based Safety of Monotone Systems: Verification and Control Synthesis","primary_cat":"eess.SY","submitted_at":"2026-05-15T21:55:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Dominance functions from a small number of trajectories serve as dissipative and expressive building blocks for formal safety certificates in monotone discrete-time systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08059","ref_index":4,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study","primary_cat":"cs.RO","submitted_at":"2026-04-09T10:18:51+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A governed upgrade framework with interface, policy, behavioral, and recovery checks keeps unsafe activations at zero across multi-round AI capability upgrades on a PyBullet/ROS 2 manipulation testbed while retaining task success near naive upgrades.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Tosupportupgradeanalysis,eachcapabilityversionisrepresentedbybothexecutablelogicandmachine-readable operationalmetadata.ThisextendstheECM abstractionintroducedinpriorwork(Qinetal.,2026a,c),wheremodules expose interfaces, permissions, risk information, rollback support, and environment-related descriptors. We represent a capability version𝑐as 𝑐= (𝐼 𝑐, 𝑂 𝑐, 𝜙 𝑐, 𝑃 𝑐, 𝐵 𝑐, 𝑅 𝑐, 𝐷 𝑐),(4) where: •𝐼 𝑐 and𝑂 𝑐 are the input and output interface specifications; •𝜙 𝑐 is the invocation schema and declarative capability descriptor; •𝑃 𝑐 is the permission and policy-relevant profile; •𝐵 𝑐 is the behavioral signature inferred from execution traces; •𝑅 𝑐 is the recovery profile, including rollback and safe-abort assumptions; •𝐷 𝑐 is deployment metadata such as version, dependencies, and environment scope."},{"citing_arxiv_id":"2602.02394","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On the Practical Implementation of a Sequential Quadratic Programming Algorithm for Nonconvex Sum-of-squares Problems","primary_cat":"math.OC","submitted_at":"2026-02-02T17:56:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A filter line search SQP algorithm reduces iterations and computation time for nonconvex SOS programs compared to prior methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.06341","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation","primary_cat":"cs.LG","submitted_at":"2025-11-09T11:51:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A scalable verification framework for neural control barrier functions uses linear bound propagation on network gradients combined with McCormick relaxations to certify safety conditions for control-affine systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}