{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:357YE3EXYC4H4EAQG2VUYOKB4F","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":"dcc713856b10ab8b4bc07981cff2788b8ed9514ee7bfd7f912e4cca96f3ed700","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T03:45:06Z","title_canon_sha256":"a15416e33e95c75dcc399e1e5c58ffdd700b48d7bca8a75b39140cb74651127e"},"schema_version":"1.0","source":{"id":"2606.25360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25360","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25360v1","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25360","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"357YE3EXYC4H","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"357YE3EXYC4H4EAQ","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"357YE3EX","created_at":"2026-06-25T01:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:d60eeea5da903eeb2957b2b8e8c94c4fa3247504ae88cb86451b1cf6c85c70e6","target":"graph","created_at":"2026-06-25T01:18:03Z","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/2606.25360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bowen Yang, Long Zeng, Siyu Chen, Tongtong Cao, Xinyu Shao, Xiu Li, Yajun Gao, Yanzhe Tang, Yuxuan Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T03:45:06Z","title":"Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25360","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":"sha256:3735e59bc6f33db6f19c2d1cb0b943f4925cbeb447b8a136af90930d1b2b9b47","target":"record","created_at":"2026-06-25T01:18:03Z","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":"dcc713856b10ab8b4bc07981cff2788b8ed9514ee7bfd7f912e4cca96f3ed700","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T03:45:06Z","title_canon_sha256":"a15416e33e95c75dcc399e1e5c58ffdd700b48d7bca8a75b39140cb74651127e"},"schema_version":"1.0","source":{"id":"2606.25360","kind":"arxiv","version":1}},"canonical_sha256":"df7f826c97c0b87e101036ab4c3941e17927e5ce83cbc8097d09d3eea6c3e45b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df7f826c97c0b87e101036ab4c3941e17927e5ce83cbc8097d09d3eea6c3e45b","first_computed_at":"2026-06-25T01:18:03.168253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:03.168253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V/GWCvennr9nusVHX5CEs//D3tbN2uTOK+MIGLosHbIkHjKC8otFCNqzDhOHlPpxM7OeH5Z7BLYduESYUjg7Bw==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:03.168620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3735e59bc6f33db6f19c2d1cb0b943f4925cbeb447b8a136af90930d1b2b9b47","sha256:d60eeea5da903eeb2957b2b8e8c94c4fa3247504ae88cb86451b1cf6c85c70e6"],"state_sha256":"cafc2ec3b9709548d9d65500cb0c00a750af6dbe13101d2e41a4b595c6c2886f"}