{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2CAGGPG4XIDHG5W2PEXRQS2FWL","short_pith_number":"pith:2CAGGPG4","schema_version":"1.0","canonical_sha256":"d080633cdcba067376da792f184b45b2ec363d9ed4097f8220dc8e44677d2234","source":{"kind":"arxiv","id":"2607.04171","version":1},"attestation_state":"computed","paper":{"title":"XS-VLA: Coupling Coarse-grained Spatial Distillation with Latent Flow Matching for Lightweight Robotic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Lei Iok Tong, QianZhi Li, Qingchen Xie, Wei Huang, Xiaolong Liu, Ying Jie Yap, Yujie Zhang, Zhidong Deng","submitted_at":"2026-07-05T08:34:39Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown strong multimodal understanding and spatial grounding, but their computational cost limits real-time robotic control. In contrast, lightweight models are suitable for edge deployment but often suffer from \"spatial blindness\", namely weak native spatial prediction ability. Training Vision-Language-Action (VLA) models on mixed human demonstrations can also degrade policy performance due to highly diverse behaviors. To address these limitations, we propose XS-VLA, a two-stage framework for efficient and spatially grounded robotic manipulation. First"},"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":"2607.04171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-05T08:34:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"077466e5a3e3847f46e0badacaef4e398d8ce1149b95786a2f5c1b18f8d2bea8","abstract_canon_sha256":"e3d244c3827e33ba6a5c5d1a9c395da8880e4a9c94a048ea78fdf1baeaad9bea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:00.836374Z","signature_b64":"rF62jOfmViO3alZe9YXY4UhSeenuDWC/Fiylo6h5lgdrJq7YkV6lQJ9nqOWaqHoA812b2Cml91hbYU29t88sCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d080633cdcba067376da792f184b45b2ec363d9ed4097f8220dc8e44677d2234","last_reissued_at":"2026-07-07T02:19:00.835716Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:00.835716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XS-VLA: Coupling Coarse-grained Spatial Distillation with Latent Flow Matching for Lightweight Robotic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Lei Iok Tong, QianZhi Li, Qingchen Xie, Wei Huang, Xiaolong Liu, Ying Jie Yap, Yujie Zhang, Zhidong Deng","submitted_at":"2026-07-05T08:34:39Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown strong multimodal understanding and spatial grounding, but their computational cost limits real-time robotic control. In contrast, lightweight models are suitable for edge deployment but often suffer from \"spatial blindness\", namely weak native spatial prediction ability. Training Vision-Language-Action (VLA) models on mixed human demonstrations can also degrade policy performance due to highly diverse behaviors. To address these limitations, we propose XS-VLA, a two-stage framework for efficient and spatially grounded robotic manipulation. First"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04171","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/2607.04171/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":"2607.04171","created_at":"2026-07-07T02:19:00.835804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04171v1","created_at":"2026-07-07T02:19:00.835804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04171","created_at":"2026-07-07T02:19:00.835804+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CAGGPG4XIDH","created_at":"2026-07-07T02:19:00.835804+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CAGGPG4XIDHG5W2","created_at":"2026-07-07T02:19:00.835804+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CAGGPG4","created_at":"2026-07-07T02:19:00.835804+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/2CAGGPG4XIDHG5W2PEXRQS2FWL","json":"https://pith.science/pith/2CAGGPG4XIDHG5W2PEXRQS2FWL.json","graph_json":"https://pith.science/api/pith-number/2CAGGPG4XIDHG5W2PEXRQS2FWL/graph.json","events_json":"https://pith.science/api/pith-number/2CAGGPG4XIDHG5W2PEXRQS2FWL/events.json","paper":"https://pith.science/paper/2CAGGPG4"},"agent_actions":{"view_html":"https://pith.science/pith/2CAGGPG4XIDHG5W2PEXRQS2FWL","download_json":"https://pith.science/pith/2CAGGPG4XIDHG5W2PEXRQS2FWL.json","view_paper":"https://pith.science/paper/2CAGGPG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04171&json=true","fetch_graph":"https://pith.science/api/pith-number/2CAGGPG4XIDHG5W2PEXRQS2FWL/graph.json","fetch_events":"https://pith.science/api/pith-number/2CAGGPG4XIDHG5W2PEXRQS2FWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CAGGPG4XIDHG5W2PEXRQS2FWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CAGGPG4XIDHG5W2PEXRQS2FWL/action/storage_attestation","attest_author":"https://pith.science/pith/2CAGGPG4XIDHG5W2PEXRQS2FWL/action/author_attestation","sign_citation":"https://pith.science/pith/2CAGGPG4XIDHG5W2PEXRQS2FWL/action/citation_signature","submit_replication":"https://pith.science/pith/2CAGGPG4XIDHG5W2PEXRQS2FWL/action/replication_record"}},"created_at":"2026-07-07T02:19:00.835804+00:00","updated_at":"2026-07-07T02:19:00.835804+00:00"}