{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2CAGGPG4XIDHG5W2PEXRQS2FWL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e3d244c3827e33ba6a5c5d1a9c395da8880e4a9c94a048ea78fdf1baeaad9bea","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-05T08:34:39Z","title_canon_sha256":"077466e5a3e3847f46e0badacaef4e398d8ce1149b95786a2f5c1b18f8d2bea8"},"schema_version":"1.0","source":{"id":"2607.04171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04171","created_at":"2026-07-07T02:19:00Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04171v1","created_at":"2026-07-07T02:19:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04171","created_at":"2026-07-07T02:19:00Z"},{"alias_kind":"pith_short_12","alias_value":"2CAGGPG4XIDH","created_at":"2026-07-07T02:19:00Z"},{"alias_kind":"pith_short_16","alias_value":"2CAGGPG4XIDHG5W2","created_at":"2026-07-07T02:19:00Z"},{"alias_kind":"pith_short_8","alias_value":"2CAGGPG4","created_at":"2026-07-07T02:19:00Z"}],"graph_snapshots":[{"event_id":"sha256:9cb9195f61fc26284dc9638c20da6ad77820a4f9e95f4474f9934a6e41abcbb9","target":"graph","created_at":"2026-07-07T02:19:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.04171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lei Iok Tong, QianZhi Li, Qingchen Xie, Wei Huang, Xiaolong Liu, Ying Jie Yap, Yujie Zhang, Zhidong Deng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-05T08:34:39Z","title":"XS-VLA: Coupling Coarse-grained Spatial Distillation with Latent Flow Matching for Lightweight Robotic Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04171","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db000dd04afd17179d632b2023a76b71a4ccc51db36f9d5130fea19a9d6c8028","target":"record","created_at":"2026-07-07T02:19:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e3d244c3827e33ba6a5c5d1a9c395da8880e4a9c94a048ea78fdf1baeaad9bea","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-05T08:34:39Z","title_canon_sha256":"077466e5a3e3847f46e0badacaef4e398d8ce1149b95786a2f5c1b18f8d2bea8"},"schema_version":"1.0","source":{"id":"2607.04171","kind":"arxiv","version":1}},"canonical_sha256":"d080633cdcba067376da792f184b45b2ec363d9ed4097f8220dc8e44677d2234","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d080633cdcba067376da792f184b45b2ec363d9ed4097f8220dc8e44677d2234","first_computed_at":"2026-07-07T02:19:00.835716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:00.835716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rF62jOfmViO3alZe9YXY4UhSeenuDWC/Fiylo6h5lgdrJq7YkV6lQJ9nqOWaqHoA812b2Cml91hbYU29t88sCw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:00.836374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db000dd04afd17179d632b2023a76b71a4ccc51db36f9d5130fea19a9d6c8028","sha256:9cb9195f61fc26284dc9638c20da6ad77820a4f9e95f4474f9934a6e41abcbb9"],"state_sha256":"49ba3b20531cd869576b1bd9dd662c6e8936cd0fd0a1bd09fa8bbbac89cfb35e"}