{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C2QEVRKDNKN2YUJRODMZTTFFBJ","short_pith_number":"pith:C2QEVRKD","schema_version":"1.0","canonical_sha256":"16a04ac5436a9bac513170d999cca50a5998d6834ad3252a50d05a0bb412c1d7","source":{"kind":"arxiv","id":"2512.22539","version":2},"attestation_state":"computed","paper":{"title":"VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Borong Zhang, Jiachen Shen, Jiahao Li, Jiaming Ji, Juntao Dai, Yaodong Yang, Yishuai Cai, Yuanpei Chen, Yuhao Zhang","submitted_at":"2025-12-27T09:40:54Z","abstract_excerpt":"While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively understand their limits and failure modes. To address this, we introduce a comprehensive benchmark called VLA-Arena. We propose a novel structured task design framework to quantify difficulty across three orthogonal axes: (1) Task Structure, (2) Language Command, and (3) Visual Observation. This allows us to systematically design tasks with fine-grained difficulty levels, enabling a precise measurement of model capability frontiers. For Task Structure, VLA-"},"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":"2512.22539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-27T09:40:54Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"53656a37e1bd78b99cd019ad2d29c2dc595cd4aa2b85a614429415d7a3fa0c39","abstract_canon_sha256":"ad360a05b2a1e3cd9b49abbbd6a0dec9a176423b2930195b5eb1891af734a2aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:47.261092Z","signature_b64":"0an7Yn3XkYK/VzundYquRvNe6PNh02H9kXiaMfNrMRL0oYdsOLeVTqoI1gz9ZWT9vCJQE6zuH8mz/u6VQatgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16a04ac5436a9bac513170d999cca50a5998d6834ad3252a50d05a0bb412c1d7","last_reissued_at":"2026-06-03T01:05:47.260612Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:47.260612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Borong Zhang, Jiachen Shen, Jiahao Li, Jiaming Ji, Juntao Dai, Yaodong Yang, Yishuai Cai, Yuanpei Chen, Yuhao Zhang","submitted_at":"2025-12-27T09:40:54Z","abstract_excerpt":"While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively understand their limits and failure modes. To address this, we introduce a comprehensive benchmark called VLA-Arena. We propose a novel structured task design framework to quantify difficulty across three orthogonal axes: (1) Task Structure, (2) Language Command, and (3) Visual Observation. This allows us to systematically design tasks with fine-grained difficulty levels, enabling a precise measurement of model capability frontiers. For Task Structure, VLA-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.22539","kind":"arxiv","version":2},"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/2512.22539/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":"2512.22539","created_at":"2026-06-03T01:05:47.260672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.22539v2","created_at":"2026-06-03T01:05:47.260672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.22539","created_at":"2026-06-03T01:05:47.260672+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2QEVRKDNKN2","created_at":"2026-06-03T01:05:47.260672+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2QEVRKDNKN2YUJR","created_at":"2026-06-03T01:05:47.260672+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2QEVRKD","created_at":"2026-06-03T01:05:47.260672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2605.23856","citing_title":"Point Tracking Improves World Action Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12160","citing_title":"Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12386","citing_title":"SafeManip: A Property-Driven Benchmark for Temporal Safety Evaluation in Robotic Manipulation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09948","citing_title":"LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23775","citing_title":"Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18000","citing_title":"Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07381","citing_title":"Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11751","citing_title":"Grounded World Model for Semantically Generalizable Planning","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ","json":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ.json","graph_json":"https://pith.science/api/pith-number/C2QEVRKDNKN2YUJRODMZTTFFBJ/graph.json","events_json":"https://pith.science/api/pith-number/C2QEVRKDNKN2YUJRODMZTTFFBJ/events.json","paper":"https://pith.science/paper/C2QEVRKD"},"agent_actions":{"view_html":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ","download_json":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ.json","view_paper":"https://pith.science/paper/C2QEVRKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.22539&json=true","fetch_graph":"https://pith.science/api/pith-number/C2QEVRKDNKN2YUJRODMZTTFFBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/C2QEVRKDNKN2YUJRODMZTTFFBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ/action/storage_attestation","attest_author":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ/action/author_attestation","sign_citation":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ/action/citation_signature","submit_replication":"https://pith.science/pith/C2QEVRKDNKN2YUJRODMZTTFFBJ/action/replication_record"}},"created_at":"2026-06-03T01:05:47.260672+00:00","updated_at":"2026-06-03T01:05:47.260672+00:00"}