{"total":26,"items":[{"citing_arxiv_id":"2606.27807","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks","primary_cat":"cs.RO","submitted_at":"2026-06-26T07:45:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SpikeVLA replaces transformer components in VLA models with spiking vision encoder, multi-modal LLM, and action policy network to reduce energy consumption while maintaining competitive performance on navigation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28237","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation","primary_cat":"cs.RO","submitted_at":"2026-05-27T09:50:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"POINav-Bench provides the first high-fidelity real-world benchmark for POI-goal VLN using 3DGS reconstructions of 126k m² with 163 POIs, supported by a Brain-Action framework and 70K real signage-entrance dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27582","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation","primary_cat":"cs.RO","submitted_at":"2026-05-26T18:52:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A zero-shot unified agent for VLN-CE, ObjectNav, EQA and Aerial-VLN on wheeled, quadruped, humanoid and UAV platforms that translates language and vision inputs into actions via MLLMs plus TDM and SCB mechanisms, matching trained foundation models on multiple benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00104","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVs","primary_cat":"cs.RO","submitted_at":"2026-05-26T10:03:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"PEACE decouples single-pass LLM planning from PX4 execution via ROS 2 and a constraint layer, with modular 3D perception, and shows feasibility in Gazebo SITL with improved explainability and fewer LLM calls.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22816","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","primary_cat":"cs.RO","submitted_at":"2026-05-21T17:58:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AwareVLN introduces a structural reasoning module and automatic data engine with progress division to equip VLN agents with self-awareness of agent state and task progress, outperforming prior methods on Habitat datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22036","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation","primary_cat":"cs.CV","submitted_at":"2026-05-21T06:20:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GA-VLN builds a geometry-aware BEV representation from RGB-D inputs plus 3D foundation model features to deliver state-of-the-art vision-language navigation using only navigation data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17249","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","primary_cat":"cs.RO","submitted_at":"2026-05-17T04:12:56+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":"2605.15517","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy","primary_cat":"cs.RO","submitted_at":"2026-05-15T01:27:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09441","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Isolation: A Unified Benchmark for General-Purpose Navigation","primary_cat":"cs.RO","submitted_at":"2026-05-10T09:34:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OmniNavBench is a unified benchmark for general-purpose navigation featuring composite multi-skill instructions, support for humanoid, quadrupedal and wheeled robots, and 1779 human teleoperated trajectories across 170 environments.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"strong potential for cross-task generalization. In parallel, there is a growing trend toward developing generalist algorithms that adapt to different robot morphologies. NavFoM [40] has been deployed across diverse platforms, including quadrupeds, drones, and wheeled robots. InternVLA-N1 [31] showcases zero-shot cross-embodiment generalization, spanning wheeled to humanoid robots, and NaVILA [7] achieves transfer for legged robots by decoupling high-level planning from low- level control. Furthermore, VLN-PE [28] highlights the im- portance of physical embodiment, revealing how sensitive existing algorithms are to robot dynamics and camera con- figurations. Collectively, these advances indicate that unified navigation models have demonstrated promising capabilities in"},{"citing_arxiv_id":"2604.27620","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation","primary_cat":"cs.CV","submitted_at":"2026-04-30T09:09:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SpaAct activates spatial awareness in VLMs using action retrospection, future frame prediction, and progressive curriculum learning to reach SOTA on VLN-CE benchmarks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Recent progress in VLN has been increasingly driven by vision- language models (VLMs) [ 6-8, 37]. Instead of relying on hand- crafted modules [ 12, 57] or simulator-specific waypoint predic- tors [2, 28], many recent methods build on large pre-trained multi- modal backbones and directly learn an end-to-end mapping from instructions and streaming observations to low-level actions [15, 26, 39, 64, 69, 78]. This paradigm is attractive because it inherits strong semantic understanding, object recognition, and instruction following capabilities from VLMs, while also offering a simple and flexible interface for embodied control. Despite their strong semantic priors, current VLM-based VLN methods still face an important limitation. As illustrated in Fig."},{"citing_arxiv_id":"2604.17473","ref_index":88,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dual-Anchoring: Addressing State Drift in Vision-Language Navigation","primary_cat":"cs.CV","submitted_at":"2026-04-19T15:03:38+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":"2604.17407","ref_index":102,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Think before Go: Hierarchical Reasoning for Image-goal Navigation","primary_cat":"cs.RO","submitted_at":"2026-04-19T12:30:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HRNav decomposes image-goal navigation into VLM-based short-horizon planning and RL-based execution with a wandering suppression penalty to improve performance in complex unseen settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14344","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CART: Context-Aware Terrain Adaptation using Temporal Sequence Selection for Legged Robots","primary_cat":"cs.RO","submitted_at":"2026-04-15T18:52:50+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":"2604.13654","ref_index":87,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","primary_cat":"cs.RO","submitted_at":"2026-04-15T09:20:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Cosmos-Reason1 [26] 2025 WM + Reasoning Physical common senseCombining world models with embodied reasoning GRaD-Nav++ [84] 2025 VLA MoE + Diff. RL in 3DGSLightweight onboard VLA at 25 Hz real-time control RaceVLA [85] 2025 VLA End-to-end FPV controlFirst VLA for high-speed autonomous drone racing TrackVLA [86] 2025 VLA Unified LLM backbone Integrated target recognition and trajectory planning NaVILA [87] 2025 Hierarchical VLM planner + RL executor Mid-level language actions bridging reasoning and control Swarm-GPT [88] 2023 LLM + Safety LLM planner + safety filter Language-based multi-UA V swarm coordination TACOS [89] 2025 LLM + MARL LLM decomposition + RL exec Hierarchical planning with safety-constrained execution SwarmVLM [90] 2025 VLM-RAG Real-time parameter tuning VLM-RAG orchestration of heterogeneous UA V-AGV swarms"},{"citing_arxiv_id":"2604.08509","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Visually-grounded Humanoid Agents","primary_cat":"cs.CV","submitted_at":"2026-04-09T17:50:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A coupled world-agent framework uses 3D Gaussian reconstruction and first-person RGB-D perception with iterative planning to enable goal-directed, collision-avoiding humanoid behavior in novel reconstructed scenes.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"agents such as high-level reasoning [109] and dialogue [63] in complex scenes. However, such systems largely remain disembodied: they are typically constrained to symbolic reasoning [89] or scripted scenarios [67] and often lack vi- sual grounding, real-world perception-action coupling, and context-aware adaptability. Some efforts integrate VLMs with visual inputs for the motion planning of agents [11], but relying solely on VLM makes it challenging to operate effec- tively in complex environments. Due to these limitations, no prior work has been able to span the spectrum from semantic reasoning to embodied digital humans with perception, deci- sion, and action fused into a continuous cycle, allowing them to adapt and act autonomously within complex, real-world"},{"citing_arxiv_id":"2604.08232","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation","primary_cat":"cs.AI","submitted_at":"2026-04-09T13:22:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HiRO-Nav adaptively triggers reasoning only on high-entropy actions via a hybrid training pipeline and shows better success-token trade-offs than always-reason or never-reason baselines on the CHORES-S benchmark.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"agent per episode and per step, respectively. RLI and RLII refer to the two stages of online RL training. Training Recipe Model Name Reasoning Strategy ASM Dataset SR%↑SEL%↑#Token/E↓#Token/S↓ TF GPT-4o [18] No-Thinking✓- 8.0 4.45.6×10 2 3.1 o3 [22] Dense-Thinking✓- 27.0 12.32.4×10 5 539.4 Gemini2.5-Pro [9] Dense-Thinking✓- 27.5 16.22.3×10 5 804.8 SFT NaVILA [7] No-Thinking×NRD 30.5 12.11.8×10 3 3.7 Qwen2.5VL-3B [1] No-Thinking×NRD 36.5 28.81.5×10 3 3.8 No-Thinking✓NRD 50.0 41.21.2×10 3 3.8 H-SFT Qwen2.5VL-3B [1] No-Thinking✓HRD 49.5 39.11.2×10 3 3.8 Thinking-Every-K-Steps✓HRD 60.0 40.34.8×10 3 17.6 Dense-Thinking✓HRD 21.0 8.23.6×10 4 72.1 Ours ✓ HRD 59.5 48.9 2.3×103 9.2 SFT+RLI NaVILA [7] No-Thinking×NRD 44."},{"citing_arxiv_id":"2604.02911","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped Robots","primary_cat":"cs.RO","submitted_at":"2026-04-03T09:27:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DreamTIP adds LLM-identified task-invariant properties as auxiliary targets in Dreamer's world model plus a mixed-replay adaptation step, delivering 28.1% average simulated transfer gains and 100% real-world climb success versus 10% for baselines.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"across three main areas: reward modeling, motion control, and representation learning. In reward design, works like Eureka [26] show LLMs can automatically generate reward functions. For motion control, some studies use LLMs to convert language into intermediate commands (e.g., foot con- tact patterns) executed by reinforcement learning controllers [27], [28], or even directly output joint trajectories [29]. In representation learning, methods such as LESR [30] employ LLMs to improve state representations and intrinsic rewards, enhancing policy generalization and efficiency. In contrast, our approach utilizes LLMs' rich knowledge and reasoning capabilities to extract Task-Invariant Properties closely tied to"},{"citing_arxiv_id":"2603.07080","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness","primary_cat":"cs.RO","submitted_at":"2026-03-07T07:30:35+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"VLN-Cache delivers up to 1.52x faster inference in VLN models by using view-aligned remapping for geometric consistency and a task-relevance saliency filter to manage semantic changes during navigation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.21714","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AstraNav-World: World Model for Foresight Control and Consistency","primary_cat":"cs.CV","submitted_at":"2025-12-25T15:31:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AstraNav-World unifies diffusion video generation and vision-language action planning in a single bidirectional model that improves trajectory accuracy, success rates, and zero-shot real-world adaptation in embodied navigation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.17097","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation","primary_cat":"cs.RO","submitted_at":"2025-11-21T09:52:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Semantic progress reasoning predicts instruction-style advancement from visual history to guide policies, yielding state-of-the-art success and efficiency on R2R-CE and RxR-CE.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.08547","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation","primary_cat":"cs.RO","submitted_at":"2025-10-09T17:55:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"R2RGen introduces a simulator-free three-stage pipeline that parses, augments, and post-processes real pointcloud observation-action pairs to improve spatial generalization in robotic manipulation policies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.01925","ref_index":153,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","primary_cat":"cs.RO","submitted_at":"2025-07-02T17:34:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The survey frames VLA models as pipelines that generate progressively grounded action tokens and classifies those tokens into eight types to guide future development.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Discussion and Future Directions One limitation ofusing languagedescriptionsas action tokens arisesfrom their imperfectexpressiveness. While natural language is flexible and interpretable, it is inherently ambiguous and often insufficient for specifying fine-grained control behaviors - particularly in contact-rich or deformable manipulation tasks [153, 154], where precise spatial and temporal details are critical. These issues may lead to miscommunication between system components and inadequate task grounding, both of which can hinder overall performance. Another limitation concernslatency. Generating high-quality language descriptions often depends on large- scale models, which can incur inference delays and constrain applicability in dynamic or real-time scenarios."},{"citing_arxiv_id":"2506.07339","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Real-Time Execution of Action Chunking Flow Policies","primary_cat":"cs.RO","submitted_at":"2025-06-09T01:01:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2504.16054","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:31:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"π_{0.5} is a VLA model that achieves long-horizon dexterous manipulation in entirely new homes through co-training on heterogeneous tasks and multi-source data including web and semantic predictions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2501.09747","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","primary_cat":"cs.RO","submitted_at":"2025-01-16T18:57:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FAST applies discrete cosine transform to robot action sequences for efficient tokenization, enabling autoregressive VLAs to succeed on high-frequency dexterous tasks and scale to 10k hours of data while matching diffusion VLA performance with up to 5x faster training.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Xu, Yichu Yang, Hanbo Zhang, and Minzhao Zhu. Gr- 2: A generative video-language-action model with web- scale knowledge for robot manipulation. arXiv preprint arXiv:2410.06158, 2024. [12] Sanyuan Chen, Yu Wu, Chengyi Wang, Shujie Liu, Daniel Tompkins, Zhuo Chen, and Furu Wei. Beats: Au- dio pre-training with acoustic tokenizers. arXiv preprint arXiv:2212.09058, 2022. [13] An-Chieh Cheng, Yandong Ji, Zhaojing Yang, Xueyan Zou, Jan Kautz, Erdem Biyik, Hongxu Yin, Sifei Liu, and Xiaolong Wang. NaVILA: Legged Robot Vision- Language-Action Model for Navigation. arXiv preprint arXiv:2412.04453, 2024. [14] Xuxin Cheng, Jialong Li, Shiqi Yang, Ge Yang, and Xiaolong Wang. Open-television: Teleoperation with immersive active visual feedback."},{"citing_arxiv_id":"2412.04468","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"NVILA: Efficient Frontier Visual Language Models","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:59:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"NVILA improves on VILA with a scale-then-compress visual token strategy and full-lifecycle efficiency optimizations, matching or exceeding leading VLMs on image and video benchmarks while reducing training cost 1.9-5.1x and latencies 1.2-2.8x.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"At each time step𝑡, the agent receives a language instruction and a video observation, plans the next action, and transitions to the next state 𝑡+ 1, where it receives a new observation. NVILA's efficient and flexible handling of multi-frame inputs enables seamless integration of historical and cur- rent observations into VLMs. The NaVILA frame- work [8] introduces a tailored navigation prompt and fine-tunes NVILA using navigation-specific SFT data Table 11|Robotic navigation. All numbers are from NaVILA, except for those of NVILA. All models are provided with only RGB inputs. We refer the readers to NaVILA [8] for more details. R2R Val-Unseen Obs. NE ↓OS↑SR↑SPL↑ Seq2Seq - RGB 10.10 8.0 0.0 0.0 CMA - RGB 9."}],"limit":50,"offset":0}