{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XWE3S4E4YNUCSKYLKS7A3TUZZK","short_pith_number":"pith:XWE3S4E4","schema_version":"1.0","canonical_sha256":"bd89b9709cc368292b0b54be0dce99caaff34bfe8f44e92eb424ea535d730d66","source":{"kind":"arxiv","id":"2606.01241","version":1},"attestation_state":"computed","paper":{"title":"OneVLA: A Unified Framework for Embodied Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenhao Zhang, Hangjun Ye, Hongsheng Li, Jinkun Liu, Lei Zhou, Lingfeng Zhang, Long Chen, Qiang Zhang, Shuyi Zhang, Wenbo Ding, Xiaojun Liang, Xiaoshuai Hao, Yingbo Tang","submitted_at":"2026-05-31T13:43:23Z","abstract_excerpt":"Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact physically with their surroundings. However, current Vision-Language-Action (VLA) models remain constrained by task-specific architectures, specializing in either navigation or manipulation, which hinders the development of general-purpose robotic agents. To bridge this gap, we introduce OneVLA, a unified architecture that integrates these distinct tasks into a single, cohesive framework. Specifically, we design a unified action head capable of "},"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":"2606.01241","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-31T13:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"462ed540c27c1d961da200e68696e4d951dc65128bd64f82820383bcd5f5501a","abstract_canon_sha256":"fca81c8e567d4f0dd6c5f1fc914b7b5bfbc98c4e1b94642347ab989afaebb5f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:27.703748Z","signature_b64":"Jt/kDoGspk+j3yKn1YMarE0dldvFfP1e65TPEgo6dc4XGcLT+uONmTEF+tfRZbgbzXl/+dgR1/rLpZ0MQ613AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd89b9709cc368292b0b54be0dce99caaff34bfe8f44e92eb424ea535d730d66","last_reissued_at":"2026-06-02T02:04:27.703310Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:27.703310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OneVLA: A Unified Framework for Embodied Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenhao Zhang, Hangjun Ye, Hongsheng Li, Jinkun Liu, Lei Zhou, Lingfeng Zhang, Long Chen, Qiang Zhang, Shuyi Zhang, Wenbo Ding, Xiaojun Liang, Xiaoshuai Hao, Yingbo Tang","submitted_at":"2026-05-31T13:43:23Z","abstract_excerpt":"Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact physically with their surroundings. However, current Vision-Language-Action (VLA) models remain constrained by task-specific architectures, specializing in either navigation or manipulation, which hinders the development of general-purpose robotic agents. To bridge this gap, we introduce OneVLA, a unified architecture that integrates these distinct tasks into a single, cohesive framework. Specifically, we design a unified action head capable of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01241","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/2606.01241/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":"2606.01241","created_at":"2026-06-02T02:04:27.703379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01241v1","created_at":"2026-06-02T02:04:27.703379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01241","created_at":"2026-06-02T02:04:27.703379+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWE3S4E4YNUC","created_at":"2026-06-02T02:04:27.703379+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWE3S4E4YNUCSKYL","created_at":"2026-06-02T02:04:27.703379+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWE3S4E4","created_at":"2026-06-02T02:04:27.703379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK","json":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK.json","graph_json":"https://pith.science/api/pith-number/XWE3S4E4YNUCSKYLKS7A3TUZZK/graph.json","events_json":"https://pith.science/api/pith-number/XWE3S4E4YNUCSKYLKS7A3TUZZK/events.json","paper":"https://pith.science/paper/XWE3S4E4"},"agent_actions":{"view_html":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK","download_json":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK.json","view_paper":"https://pith.science/paper/XWE3S4E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01241&json=true","fetch_graph":"https://pith.science/api/pith-number/XWE3S4E4YNUCSKYLKS7A3TUZZK/graph.json","fetch_events":"https://pith.science/api/pith-number/XWE3S4E4YNUCSKYLKS7A3TUZZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK/action/storage_attestation","attest_author":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK/action/author_attestation","sign_citation":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK/action/citation_signature","submit_replication":"https://pith.science/pith/XWE3S4E4YNUCSKYLKS7A3TUZZK/action/replication_record"}},"created_at":"2026-06-02T02:04:27.703379+00:00","updated_at":"2026-06-02T02:04:27.703379+00:00"}