{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6WUXVKTCALV2YBVI7ZHMXDEMDP","short_pith_number":"pith:6WUXVKTC","schema_version":"1.0","canonical_sha256":"f5a97aaa6202ebac06a8fe4ecb8c8c1bf11722847d6d53b22dcb14af53fd5b45","source":{"kind":"arxiv","id":"2606.30645","version":1},"attestation_state":"computed","paper":{"title":"VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Angjoo Kanazawa, Carmelo Sferrazza, Guanya Shi, Jiaman Li, Karen Liu, Koushil Sreenath, Pei Xu, Pieter Abbeel, Rocky Duan, Sirui Chen, Takara E. Truong, Yen-Jen Wang","submitted_at":"2026-06-29T17:59:55Z","abstract_excerpt":"Perception-based humanoid loco-manipulation requires connecting egocentric observations and task instructions to whole-body motion. Learning this mapping requires synchronized egocentric images, language commands, and robot-compatible kinematic trajectories, yet no existing data source provides this complete tuple at scale. We address this bottleneck by generating vision-language-kinematics (VLK) supervision synthetically in reconstructed scenes. Our pipeline leverages 3D Gaussian Splatting to reconstruct metric-scale indoor environments, synthesizes navigation and object-interaction trajector"},"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":"2606.30645","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T17:59:55Z","cross_cats_sorted":["cs.AI","cs.GR","cs.SY","eess.SY"],"title_canon_sha256":"fccab2a30b424212fc9f46841ccc3a9257732efd52cc8246aaec18cbf6ddd22f","abstract_canon_sha256":"73395abe299083e58fb0f8357498177e20114654bb474a1a166dbfd591c20f7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:24.223104Z","signature_b64":"Paogkx85R8RMHvXGur1RCKO4SpVDwupbg8gYXVwnTh1fYDRuw/U5PKCV8lGjBvniAHrH5D0mp2pqacLLv/XhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5a97aaa6202ebac06a8fe4ecb8c8c1bf11722847d6d53b22dcb14af53fd5b45","last_reissued_at":"2026-06-30T02:18:24.222158Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:24.222158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Angjoo Kanazawa, Carmelo Sferrazza, Guanya Shi, Jiaman Li, Karen Liu, Koushil Sreenath, Pei Xu, Pieter Abbeel, Rocky Duan, Sirui Chen, Takara E. Truong, Yen-Jen Wang","submitted_at":"2026-06-29T17:59:55Z","abstract_excerpt":"Perception-based humanoid loco-manipulation requires connecting egocentric observations and task instructions to whole-body motion. Learning this mapping requires synchronized egocentric images, language commands, and robot-compatible kinematic trajectories, yet no existing data source provides this complete tuple at scale. We address this bottleneck by generating vision-language-kinematics (VLK) supervision synthetically in reconstructed scenes. Our pipeline leverages 3D Gaussian Splatting to reconstruct metric-scale indoor environments, synthesizes navigation and object-interaction trajector"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30645","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/2606.30645/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":"2606.30645","created_at":"2026-06-30T02:18:24.222334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30645v1","created_at":"2026-06-30T02:18:24.222334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30645","created_at":"2026-06-30T02:18:24.222334+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WUXVKTCALV2","created_at":"2026-06-30T02:18:24.222334+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WUXVKTCALV2YBVI","created_at":"2026-06-30T02:18:24.222334+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WUXVKTC","created_at":"2026-06-30T02:18:24.222334+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/6WUXVKTCALV2YBVI7ZHMXDEMDP","json":"https://pith.science/pith/6WUXVKTCALV2YBVI7ZHMXDEMDP.json","graph_json":"https://pith.science/api/pith-number/6WUXVKTCALV2YBVI7ZHMXDEMDP/graph.json","events_json":"https://pith.science/api/pith-number/6WUXVKTCALV2YBVI7ZHMXDEMDP/events.json","paper":"https://pith.science/paper/6WUXVKTC"},"agent_actions":{"view_html":"https://pith.science/pith/6WUXVKTCALV2YBVI7ZHMXDEMDP","download_json":"https://pith.science/pith/6WUXVKTCALV2YBVI7ZHMXDEMDP.json","view_paper":"https://pith.science/paper/6WUXVKTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30645&json=true","fetch_graph":"https://pith.science/api/pith-number/6WUXVKTCALV2YBVI7ZHMXDEMDP/graph.json","fetch_events":"https://pith.science/api/pith-number/6WUXVKTCALV2YBVI7ZHMXDEMDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WUXVKTCALV2YBVI7ZHMXDEMDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WUXVKTCALV2YBVI7ZHMXDEMDP/action/storage_attestation","attest_author":"https://pith.science/pith/6WUXVKTCALV2YBVI7ZHMXDEMDP/action/author_attestation","sign_citation":"https://pith.science/pith/6WUXVKTCALV2YBVI7ZHMXDEMDP/action/citation_signature","submit_replication":"https://pith.science/pith/6WUXVKTCALV2YBVI7ZHMXDEMDP/action/replication_record"}},"created_at":"2026-06-30T02:18:24.222334+00:00","updated_at":"2026-06-30T02:18:24.222334+00:00"}