{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S5LGCRXRYAZ3BSFIAQ52OQ4HWC","short_pith_number":"pith:S5LGCRXR","schema_version":"1.0","canonical_sha256":"97566146f1c033b0c8a8043ba74387b0acd109e388c68fa64db32a10dca8857d","source":{"kind":"arxiv","id":"2607.12894","version":1},"attestation_state":"computed","paper":{"title":"Hy-Embodied-VLM-1.0: Efficient Physical-World Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Yuan, Han Hu, He Zhang, Hongsheng Wu, Mingqi Gao, Oran Wang, Rui Huang, Shenghao Zhang, Xiaoran Xu, Xumin Yu, Xu Tan, Yani Zhang, Yifu Yuan, Yonggen Ling, Yongming Rao, Yuchen Zhou, Yufei Huang, Yunheng Li, Yves Liang, Zhengyou Zhang, Ziyi Wang, Zuyan Liu","submitted_at":"2026-07-14T15:34:17Z","abstract_excerpt":"Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world. In this report, we introduce Hy-Embodied-VLM-1.0, an efficient and powerful embodied foundation model specifically designed for embodied agents operating in the physical world. To cultivate such capabilities from the pre-training stage onward, we define an action-centric capability taxonomy comprising three progressive dimensions: Action-Relevant State Understanding, Actio"},"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":"2607.12894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-14T15:34:17Z","cross_cats_sorted":[],"title_canon_sha256":"08c4121b89d4ec83fbde140cb64328fbbebaa81294a713946522b8c76d63a4d7","abstract_canon_sha256":"c40c4161326e62a2f2475f1f79261dbfd9eb5cca5d50866fe90223990225e940"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:22:23.813989Z","signature_b64":"0NZcwoM506C8b/ZlGR8EUdLxBlVtVBYbn15O0oMr9edMzre5QFIfHCZ9/kp5sHScEa3jv9A3ihc9/ByGOAtSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97566146f1c033b0c8a8043ba74387b0acd109e388c68fa64db32a10dca8857d","last_reissued_at":"2026-07-15T01:22:23.813177Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:22:23.813177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hy-Embodied-VLM-1.0: Efficient Physical-World Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Yuan, Han Hu, He Zhang, Hongsheng Wu, Mingqi Gao, Oran Wang, Rui Huang, Shenghao Zhang, Xiaoran Xu, Xumin Yu, Xu Tan, Yani Zhang, Yifu Yuan, Yonggen Ling, Yongming Rao, Yuchen Zhou, Yufei Huang, Yunheng Li, Yves Liang, Zhengyou Zhang, Ziyi Wang, Zuyan Liu","submitted_at":"2026-07-14T15:34:17Z","abstract_excerpt":"Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world. In this report, we introduce Hy-Embodied-VLM-1.0, an efficient and powerful embodied foundation model specifically designed for embodied agents operating in the physical world. To cultivate such capabilities from the pre-training stage onward, we define an action-centric capability taxonomy comprising three progressive dimensions: Action-Relevant State Understanding, Actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12894","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/2607.12894/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":"2607.12894","created_at":"2026-07-15T01:22:23.813597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.12894v1","created_at":"2026-07-15T01:22:23.813597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12894","created_at":"2026-07-15T01:22:23.813597+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5LGCRXRYAZ3","created_at":"2026-07-15T01:22:23.813597+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5LGCRXRYAZ3BSFI","created_at":"2026-07-15T01:22:23.813597+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5LGCRXR","created_at":"2026-07-15T01:22:23.813597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06756","citing_title":"Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC","json":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC.json","graph_json":"https://pith.science/api/pith-number/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/graph.json","events_json":"https://pith.science/api/pith-number/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/events.json","paper":"https://pith.science/paper/S5LGCRXR"},"agent_actions":{"view_html":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC","download_json":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC.json","view_paper":"https://pith.science/paper/S5LGCRXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.12894&json=true","fetch_graph":"https://pith.science/api/pith-number/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/graph.json","fetch_events":"https://pith.science/api/pith-number/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/action/storage_attestation","attest_author":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/action/author_attestation","sign_citation":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/action/citation_signature","submit_replication":"https://pith.science/pith/S5LGCRXRYAZ3BSFIAQ52OQ4HWC/action/replication_record"}},"created_at":"2026-07-15T01:22:23.813597+00:00","updated_at":"2026-07-15T01:22:23.813597+00:00"}