{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6RVPIZG4EYLF4AMT72MOTLFMOX","short_pith_number":"pith:6RVPIZG4","schema_version":"1.0","canonical_sha256":"f46af464dc26165e0193fe98e9acac75faedf11d96b92043b1a8d58bb6b8fb8d","source":{"kind":"arxiv","id":"2412.18194","version":1},"attestation_state":"computed","paper":{"title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Peiju Liu, Qinghui Gao, Shiduo Zhang, Xiaopeng Yu, Xipeng Qiu, Yuan Li, Yu-Gang Jiang, Zhangyue Yin, Zhaoye Fei, Zhe Xu, Zuxuan Wu","submitted_at":"2024-12-24T06:03:42Z","abstract_excerpt":"General-purposed embodied agents are designed to understand the users' natural instructions or intentions and act precisely to complete universal tasks. Recently, methods based on foundation models especially Vision-Language-Action models (VLAs) have shown a substantial potential to solve language-conditioned manipulation (LCM) tasks well. However, existing benchmarks do not adequately meet the needs of VLAs and relative algorithms. To better define such general-purpose tasks in the context of LLMs and advance the research in VLAs, we present VLABench, an open-source benchmark for evaluating u"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.18194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-24T06:03:42Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"1d3553f4645dc02bcd6649749b2557e87545ec07f36fcceecc1154720f9520ae","abstract_canon_sha256":"79c6443905b94f51047c4c80194a51863e1813a3910ce59c5ccff24006b5065d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:51.370129Z","signature_b64":"2CdkUiGy9ccv3rm6IKBZH8fGIzoJbzg3ZlqT1zsekCHRjMASrrzkhYL3uSvbxHQKcJp+NNpM5s0T/+054l3UAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f46af464dc26165e0193fe98e9acac75faedf11d96b92043b1a8d58bb6b8fb8d","last_reissued_at":"2026-07-05T09:53:51.369642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:51.369642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Peiju Liu, Qinghui Gao, Shiduo Zhang, Xiaopeng Yu, Xipeng Qiu, Yuan Li, Yu-Gang Jiang, Zhangyue Yin, Zhaoye Fei, Zhe Xu, Zuxuan Wu","submitted_at":"2024-12-24T06:03:42Z","abstract_excerpt":"General-purposed embodied agents are designed to understand the users' natural instructions or intentions and act precisely to complete universal tasks. Recently, methods based on foundation models especially Vision-Language-Action models (VLAs) have shown a substantial potential to solve language-conditioned manipulation (LCM) tasks well. However, existing benchmarks do not adequately meet the needs of VLAs and relative algorithms. To better define such general-purpose tasks in the context of LLMs and advance the research in VLAs, we present VLABench, an open-source benchmark for evaluating u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18194","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.18194/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.18194","created_at":"2026-07-05T09:53:51.369700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18194v1","created_at":"2026-07-05T09:53:51.369700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18194","created_at":"2026-07-05T09:53:51.369700+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RVPIZG4EYLF","created_at":"2026-07-05T09:53:51.369700+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RVPIZG4EYLF4AMT","created_at":"2026-07-05T09:53:51.369700+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RVPIZG4","created_at":"2026-07-05T09:53:51.369700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06370","citing_title":"Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19297","citing_title":"Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02195","citing_title":"Bridge-WA: Predicting Where and How the World Changes for Robotic Action","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10382","citing_title":"UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10366","citing_title":"A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09669","citing_title":"SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07723","citing_title":"VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03784","citing_title":"Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02277","citing_title":"RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27759","citing_title":"Colosseum V2: Benchmarking Generalization for Vision Language Action Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2503.03480","citing_title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10408","citing_title":"VISOR: A Vision-Language Model-based Test Oracle for Testing Robots","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18727","citing_title":"DexHoldem: Playing Texas Hold'em with Dexterous Embodied System","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":276,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13966","citing_title":"vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":240,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10408","citing_title":"VISOR: A Vision-Language Model-based Test Oracle for Testing Robots","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06311","citing_title":"Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX","json":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX.json","graph_json":"https://pith.science/api/pith-number/6RVPIZG4EYLF4AMT72MOTLFMOX/graph.json","events_json":"https://pith.science/api/pith-number/6RVPIZG4EYLF4AMT72MOTLFMOX/events.json","paper":"https://pith.science/paper/6RVPIZG4"},"agent_actions":{"view_html":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX","download_json":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX.json","view_paper":"https://pith.science/paper/6RVPIZG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18194&json=true","fetch_graph":"https://pith.science/api/pith-number/6RVPIZG4EYLF4AMT72MOTLFMOX/graph.json","fetch_events":"https://pith.science/api/pith-number/6RVPIZG4EYLF4AMT72MOTLFMOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX/action/storage_attestation","attest_author":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX/action/author_attestation","sign_citation":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX/action/citation_signature","submit_replication":"https://pith.science/pith/6RVPIZG4EYLF4AMT72MOTLFMOX/action/replication_record"}},"created_at":"2026-07-05T09:53:51.369700+00:00","updated_at":"2026-07-05T09:53:51.369700+00:00"}