{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YSY4GYBVJDWTPOS24YQKVZ4LNW","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":"f83f3442cee0959e8a151a12449bfd2027a01b6396491e75c20727aeb97ea4dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T04:16:24Z","title_canon_sha256":"8533d34d1babb0610e735ffcb3586b0bb4ed7f1478e41c5bd3bddb225d5a1549"},"schema_version":"1.0","source":{"id":"2606.06891","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06891","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06891v1","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06891","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"YSY4GYBVJDWT","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"YSY4GYBVJDWTPOS2","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"YSY4GYBV","created_at":"2026-06-08T01:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:17ca3977f54ee619e7ed2e9ec3bcdf66f18ba304db4b0af865700954e4652b30","target":"graph","created_at":"2026-06-08T01:04:34Z","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/2606.06891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In this paper, we present an online 3D vision-language model that enables real-time spatial understanding from streaming video. Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token prediction objective to learn when to respond, and employs a lightweight Visual-Spatial Feature Integration (VSFI) module to incrementally inject temporally aligned geometry priors into the visual stream","authors_text":"Boqiang Zhang, Dong Yu, Hanxun Yu, Jianke Zhu, Lei Ke, Xuan Qu, Yuxin Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T04:16:24Z","title":"Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06891","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:c507e9518036b227a9a2cccfb8577ac70242fa72dc1949f158631e8d51a18505","target":"record","created_at":"2026-06-08T01:04:34Z","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":"f83f3442cee0959e8a151a12449bfd2027a01b6396491e75c20727aeb97ea4dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T04:16:24Z","title_canon_sha256":"8533d34d1babb0610e735ffcb3586b0bb4ed7f1478e41c5bd3bddb225d5a1549"},"schema_version":"1.0","source":{"id":"2606.06891","kind":"arxiv","version":1}},"canonical_sha256":"c4b1c3603548ed37ba5ae620aae78b6d9637bbec85cc61e1dd39e57eaba2d605","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4b1c3603548ed37ba5ae620aae78b6d9637bbec85cc61e1dd39e57eaba2d605","first_computed_at":"2026-06-08T01:04:34.263895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:34.263895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+RvuPSbCgV8hn0NsRfE4TWgpseJenC+Tj3s6iM7hLo0OVBKc47pxMtOVJE92k4TKV7rA3dOmRIBU0hW8HriHBw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:34.264768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06891","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c507e9518036b227a9a2cccfb8577ac70242fa72dc1949f158631e8d51a18505","sha256:17ca3977f54ee619e7ed2e9ec3bcdf66f18ba304db4b0af865700954e4652b30"],"state_sha256":"2897e1435f0a1de4497b53ce4e9008e84c2dd3f491e344996708ea9a8b3a3ca3"}