{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XZWNON3O7VXVBGHNCX7IJF4IEV","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":"79c22552fadb693253785709ecf5b7ca6dc06d7fd4d07c4eebc6cf33c43914cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T10:32:53Z","title_canon_sha256":"9375062f0e917697992c3c372b0a43e16b1892e763a0d63ff96143837a4a1120"},"schema_version":"1.0","source":{"id":"2605.22283","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22283","created_at":"2026-05-22T01:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22283v1","created_at":"2026-05-22T01:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22283","created_at":"2026-05-22T01:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"XZWNON3O7VXV","created_at":"2026-05-22T01:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"XZWNON3O7VXVBGHN","created_at":"2026-05-22T01:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"XZWNON3O","created_at":"2026-05-22T01:04:36Z"}],"graph_snapshots":[{"event_id":"sha256:8521d99f1ccad0aef17749ceb880286a38ded46fb63cfc450c69452aae58d679","target":"graph","created_at":"2026-05-22T01:04:36Z","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/2605.22283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly assume that task-relevant objects are always visible, leading to brittle and reactive behaviors when targets fall outside the camera's field of view. SOMA addresses this limitation by equipping VLAs with a persistent spatial memory constructed from multi-view observations acquired via a movable head camera, enabling reasoning beyond the current visual frustum. The framework consists of three components: Spatial Memory Construction, which aggregate","authors_text":"He Zhang, Hui Xiong, Pengteng Li, Tiefu Cai, Weiyu Guo, Xiao He, Yandong Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T10:32:53Z","title":"Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22283","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":"sha256:54cc50b9df0278d405ecdf17624fc4241df5c458acfbc1a6dfd2b4917bb4dbe3","target":"record","created_at":"2026-05-22T01:04:36Z","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":"79c22552fadb693253785709ecf5b7ca6dc06d7fd4d07c4eebc6cf33c43914cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T10:32:53Z","title_canon_sha256":"9375062f0e917697992c3c372b0a43e16b1892e763a0d63ff96143837a4a1120"},"schema_version":"1.0","source":{"id":"2605.22283","kind":"arxiv","version":1}},"canonical_sha256":"be6cd7376efd6f5098ed15fe849788256dc166fa761faa6c5508a66d623e3b53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be6cd7376efd6f5098ed15fe849788256dc166fa761faa6c5508a66d623e3b53","first_computed_at":"2026-05-22T01:04:36.088993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:36.088993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TjZKvOHP5LK4rVWUTt4d9JhUK/67hvzH8MAsma4lAGJyjmSgITf1ZakUge1XUINfjmWCZX5e+0w1yh/3uwaaDA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:36.089758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22283","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54cc50b9df0278d405ecdf17624fc4241df5c458acfbc1a6dfd2b4917bb4dbe3","sha256:8521d99f1ccad0aef17749ceb880286a38ded46fb63cfc450c69452aae58d679"],"state_sha256":"f26d196b25ac6a302a3f1d78b284013dcf9de4f53069b3c0a69299d7111f5cd4"}