{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C2QEVRKDNKN2YUJRODMZTTFFBJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ad360a05b2a1e3cd9b49abbbd6a0dec9a176423b2930195b5eb1891af734a2aa","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-27T09:40:54Z","title_canon_sha256":"53656a37e1bd78b99cd019ad2d29c2dc595cd4aa2b85a614429415d7a3fa0c39"},"schema_version":"1.0","source":{"id":"2512.22539","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.22539","created_at":"2026-06-03T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2512.22539v2","created_at":"2026-06-03T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.22539","created_at":"2026-06-03T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"C2QEVRKDNKN2","created_at":"2026-06-03T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"C2QEVRKDNKN2YUJR","created_at":"2026-06-03T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"C2QEVRKD","created_at":"2026-06-03T01:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:3d0a75bb8e861072134a9bc57934339ca3dd0ec7edd0917a42270a618830c2be","target":"graph","created_at":"2026-06-03T01:05:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2512.22539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","authors_text":"Borong Zhang, Jiachen Shen, Jiahao Li, Jiaming Ji, Juntao Dai, Yaodong Yang, Yishuai Cai, Yuanpei Chen, Yuhao Zhang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-27T09:40:54Z","title":"VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.22539","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fb58232cee97e92bd1bd32193e940290e115a1a73053957dc6c5123541cb80c5","target":"record","created_at":"2026-06-03T01:05:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ad360a05b2a1e3cd9b49abbbd6a0dec9a176423b2930195b5eb1891af734a2aa","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-12-27T09:40:54Z","title_canon_sha256":"53656a37e1bd78b99cd019ad2d29c2dc595cd4aa2b85a614429415d7a3fa0c39"},"schema_version":"1.0","source":{"id":"2512.22539","kind":"arxiv","version":2}},"canonical_sha256":"16a04ac5436a9bac513170d999cca50a5998d6834ad3252a50d05a0bb412c1d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16a04ac5436a9bac513170d999cca50a5998d6834ad3252a50d05a0bb412c1d7","first_computed_at":"2026-06-03T01:05:47.260612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:47.260612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0an7Yn3XkYK/VzundYquRvNe6PNh02H9kXiaMfNrMRL0oYdsOLeVTqoI1gz9ZWT9vCJQE6zuH8mz/u6VQatgDQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:47.261092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.22539","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb58232cee97e92bd1bd32193e940290e115a1a73053957dc6c5123541cb80c5","sha256:3d0a75bb8e861072134a9bc57934339ca3dd0ec7edd0917a42270a618830c2be"],"state_sha256":"adacf0d176214ff09fc742f83f472915f620d5bd3939d1a91cbc94a5fa1172dc"}