{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RNHARHC7VBF4ZRXPGQLPBSFL2Z","short_pith_number":"pith:RNHARHC7","schema_version":"1.0","canonical_sha256":"8b4e089c5fa84bccc6ef3416f0c8abd64e1497042fa723d7f451c9c4c82e988d","source":{"kind":"arxiv","id":"2607.08639","version":1},"attestation_state":"computed","paper":{"title":"Native Video-Action Pretraining for Generalizable Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaojian Li, Fangyi Xu, Gangwei Xu, Guanxing Lu, Jiahao Shao, Jiaming Zhou, Jiapeng Zhu, Jiaqi Liao, Junke Wang, Ka Leong Cheng, Lin Li, Luyao Zhang, Nan Xue, Qihang Zhang, Ruilin Wang, Shuailei Ma, Shuaiting Li, Shuai Yang, Weixuan Tang, Xing Zhu, Xinyang Wang, Yiming Luo, Yinghao Xu, Yishu Shen, Yongkun Wen, Yudong Jin, Yujie Zhao, Yujun Shen, Zifan Shi","submitted_at":"2026-07-09T16:15:43Z","abstract_excerpt":"The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation is inherently inadequate for physical environments. To bridge this gap, we present LingBot-VA 2.0, a video-action foundation model built from the ground up for embodiment. Four core design principles showcase its evolution from LingBot-VA. (1) Departing from traditional reconstruction-focused VAEs, we introduce a semantic visual-action tokenizer, which aligns visual representations with both semantics and actions, imp"},"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":"2607.08639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-09T16:15:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"108e1e90553cd47d14d34457617df13901bc8e73137f34cb2586d42a5c3744ef","abstract_canon_sha256":"11c76ec1b9904ec287b95a47c3bb922dc0a0ebed80ca66af4e1ef599031bab2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:56.270440Z","signature_b64":"upFjityePrJ9kObq7GKevccyrdB7fxeRU/E5qOzhn2UOgmKQV3elaurU6gy3Z2NVU7VnMi6l/+ptEjeoDBclCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b4e089c5fa84bccc6ef3416f0c8abd64e1497042fa723d7f451c9c4c82e988d","last_reissued_at":"2026-07-10T01:19:56.269950Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:56.269950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Native Video-Action Pretraining for Generalizable Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaojian Li, Fangyi Xu, Gangwei Xu, Guanxing Lu, Jiahao Shao, Jiaming Zhou, Jiapeng Zhu, Jiaqi Liao, Junke Wang, Ka Leong Cheng, Lin Li, Luyao Zhang, Nan Xue, Qihang Zhang, Ruilin Wang, Shuailei Ma, Shuaiting Li, Shuai Yang, Weixuan Tang, Xing Zhu, Xinyang Wang, Yiming Luo, Yinghao Xu, Yishu Shen, Yongkun Wen, Yudong Jin, Yujie Zhao, Yujun Shen, Zifan Shi","submitted_at":"2026-07-09T16:15:43Z","abstract_excerpt":"The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation is inherently inadequate for physical environments. To bridge this gap, we present LingBot-VA 2.0, a video-action foundation model built from the ground up for embodiment. Four core design principles showcase its evolution from LingBot-VA. (1) Departing from traditional reconstruction-focused VAEs, we introduce a semantic visual-action tokenizer, which aligns visual representations with both semantics and actions, imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08639","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/2607.08639/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":"2607.08639","created_at":"2026-07-10T01:19:56.270013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08639v1","created_at":"2026-07-10T01:19:56.270013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08639","created_at":"2026-07-10T01:19:56.270013+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNHARHC7VBF4","created_at":"2026-07-10T01:19:56.270013+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNHARHC7VBF4ZRXP","created_at":"2026-07-10T01:19:56.270013+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNHARHC7","created_at":"2026-07-10T01:19:56.270013+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/RNHARHC7VBF4ZRXPGQLPBSFL2Z","json":"https://pith.science/pith/RNHARHC7VBF4ZRXPGQLPBSFL2Z.json","graph_json":"https://pith.science/api/pith-number/RNHARHC7VBF4ZRXPGQLPBSFL2Z/graph.json","events_json":"https://pith.science/api/pith-number/RNHARHC7VBF4ZRXPGQLPBSFL2Z/events.json","paper":"https://pith.science/paper/RNHARHC7"},"agent_actions":{"view_html":"https://pith.science/pith/RNHARHC7VBF4ZRXPGQLPBSFL2Z","download_json":"https://pith.science/pith/RNHARHC7VBF4ZRXPGQLPBSFL2Z.json","view_paper":"https://pith.science/paper/RNHARHC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08639&json=true","fetch_graph":"https://pith.science/api/pith-number/RNHARHC7VBF4ZRXPGQLPBSFL2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/RNHARHC7VBF4ZRXPGQLPBSFL2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNHARHC7VBF4ZRXPGQLPBSFL2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNHARHC7VBF4ZRXPGQLPBSFL2Z/action/storage_attestation","attest_author":"https://pith.science/pith/RNHARHC7VBF4ZRXPGQLPBSFL2Z/action/author_attestation","sign_citation":"https://pith.science/pith/RNHARHC7VBF4ZRXPGQLPBSFL2Z/action/citation_signature","submit_replication":"https://pith.science/pith/RNHARHC7VBF4ZRXPGQLPBSFL2Z/action/replication_record"}},"created_at":"2026-07-10T01:19:56.270013+00:00","updated_at":"2026-07-10T01:19:56.270013+00:00"}