{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:357YE3EXYC4H4EAQG2VUYOKB4F","short_pith_number":"pith:357YE3EX","schema_version":"1.0","canonical_sha256":"df7f826c97c0b87e101036ab4c3941e17927e5ce83cbc8097d09d3eea6c3e45b","source":{"kind":"arxiv","id":"2606.25360","version":1},"attestation_state":"computed","paper":{"title":"Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bowen Yang, Long Zeng, Siyu Chen, Tongtong Cao, Xinyu Shao, Xiu Li, Yajun Gao, Yanzhe Tang, Yuxuan Hu","submitted_at":"2026-06-24T03:45:06Z","abstract_excerpt":"While end-to-end Vision-Language-Action (VLA) models show promise in robotic manipulation, their monolithic paradigm inherently couples semantic reasoning and spatial control. This creates a severe alignment bottleneck, limiting precise target disambiguation in data-constrained imitation learning. To overcome this, we propose SVP-IL, a decoupled architecture that explicitly extracts spatial visual grounding from the action generation loop. By leveraging vision-language foundation models, we parse instructions into zero-shot geometric masks, translating language into explicit Spatial Visual Pro"},"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":"2606.25360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T03:45:06Z","cross_cats_sorted":[],"title_canon_sha256":"a15416e33e95c75dcc399e1e5c58ffdd700b48d7bca8a75b39140cb74651127e","abstract_canon_sha256":"dcc713856b10ab8b4bc07981cff2788b8ed9514ee7bfd7f912e4cca96f3ed700"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:03.168620Z","signature_b64":"V/GWCvennr9nusVHX5CEs//D3tbN2uTOK+MIGLosHbIkHjKC8otFCNqzDhOHlPpxM7OeH5Z7BLYduESYUjg7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df7f826c97c0b87e101036ab4c3941e17927e5ce83cbc8097d09d3eea6c3e45b","last_reissued_at":"2026-06-25T01:18:03.168253Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:03.168253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bowen Yang, Long Zeng, Siyu Chen, Tongtong Cao, Xinyu Shao, Xiu Li, Yajun Gao, Yanzhe Tang, Yuxuan Hu","submitted_at":"2026-06-24T03:45:06Z","abstract_excerpt":"While end-to-end Vision-Language-Action (VLA) models show promise in robotic manipulation, their monolithic paradigm inherently couples semantic reasoning and spatial control. This creates a severe alignment bottleneck, limiting precise target disambiguation in data-constrained imitation learning. To overcome this, we propose SVP-IL, a decoupled architecture that explicitly extracts spatial visual grounding from the action generation loop. By leveraging vision-language foundation models, we parse instructions into zero-shot geometric masks, translating language into explicit Spatial Visual Pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25360","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/2606.25360/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":"2606.25360","created_at":"2026-06-25T01:18:03.168325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25360v1","created_at":"2026-06-25T01:18:03.168325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25360","created_at":"2026-06-25T01:18:03.168325+00:00"},{"alias_kind":"pith_short_12","alias_value":"357YE3EXYC4H","created_at":"2026-06-25T01:18:03.168325+00:00"},{"alias_kind":"pith_short_16","alias_value":"357YE3EXYC4H4EAQ","created_at":"2026-06-25T01:18:03.168325+00:00"},{"alias_kind":"pith_short_8","alias_value":"357YE3EX","created_at":"2026-06-25T01:18:03.168325+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/357YE3EXYC4H4EAQG2VUYOKB4F","json":"https://pith.science/pith/357YE3EXYC4H4EAQG2VUYOKB4F.json","graph_json":"https://pith.science/api/pith-number/357YE3EXYC4H4EAQG2VUYOKB4F/graph.json","events_json":"https://pith.science/api/pith-number/357YE3EXYC4H4EAQG2VUYOKB4F/events.json","paper":"https://pith.science/paper/357YE3EX"},"agent_actions":{"view_html":"https://pith.science/pith/357YE3EXYC4H4EAQG2VUYOKB4F","download_json":"https://pith.science/pith/357YE3EXYC4H4EAQG2VUYOKB4F.json","view_paper":"https://pith.science/paper/357YE3EX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25360&json=true","fetch_graph":"https://pith.science/api/pith-number/357YE3EXYC4H4EAQG2VUYOKB4F/graph.json","fetch_events":"https://pith.science/api/pith-number/357YE3EXYC4H4EAQG2VUYOKB4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/357YE3EXYC4H4EAQG2VUYOKB4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/357YE3EXYC4H4EAQG2VUYOKB4F/action/storage_attestation","attest_author":"https://pith.science/pith/357YE3EXYC4H4EAQG2VUYOKB4F/action/author_attestation","sign_citation":"https://pith.science/pith/357YE3EXYC4H4EAQG2VUYOKB4F/action/citation_signature","submit_replication":"https://pith.science/pith/357YE3EXYC4H4EAQG2VUYOKB4F/action/replication_record"}},"created_at":"2026-06-25T01:18:03.168325+00:00","updated_at":"2026-06-25T01:18:03.168325+00:00"}