{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V3T4YEYY7QLA4LTMTMO3XO6JGD","short_pith_number":"pith:V3T4YEYY","schema_version":"1.0","canonical_sha256":"aee7cc1318fc160e2e6c9b1dbbbbc930ccabdb50e477378f20d13504cfb1280b","source":{"kind":"arxiv","id":"2607.19228","version":1},"attestation_state":"computed","paper":{"title":"IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingwen Zhang, Fangzhou Hong, Hao Li, Kuixuan Jiao, Liu Liu, Tingyang Xiao, Xiaolin Zhou, Zhengyu Zou, Zhizhong Su, Ziwei Liu","submitted_at":"2026-07-21T16:00:01Z","abstract_excerpt":"Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding. Meanwhile, existing semantic reconstruction and 3D-aware vision-language methods largely rely on externally extracted 2D semantic cues or loosely coupled geometry inputs, limiting unified geometry-instance learning in long dynamic s"},"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":"2607.19228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T16:00:01Z","cross_cats_sorted":[],"title_canon_sha256":"f2a9114646915d2fc70e3711f0f628974a972275978ba6afb847aefbc8079052","abstract_canon_sha256":"a64de2d957ed3efa6004d5bae8e7dd7ff9a614b488df2a74eb64830ce6169e28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:24:15.424798Z","signature_b64":"SH+c8R7Igop4U/uQIm3pV5J5CzD6nvPbeK7QJSVsZa0vKpbaIM701MCy/jMRhoCKcAFFvOMENlj6mevxza+6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aee7cc1318fc160e2e6c9b1dbbbbc930ccabdb50e477378f20d13504cfb1280b","last_reissued_at":"2026-07-22T01:24:15.423964Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:24:15.423964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingwen Zhang, Fangzhou Hong, Hao Li, Kuixuan Jiao, Liu Liu, Tingyang Xiao, Xiaolin Zhou, Zhengyu Zou, Zhizhong Su, Ziwei Liu","submitted_at":"2026-07-21T16:00:01Z","abstract_excerpt":"Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding. Meanwhile, existing semantic reconstruction and 3D-aware vision-language methods largely rely on externally extracted 2D semantic cues or loosely coupled geometry inputs, limiting unified geometry-instance learning in long dynamic s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19228","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/2607.19228/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":"2607.19228","created_at":"2026-07-22T01:24:15.424401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19228v1","created_at":"2026-07-22T01:24:15.424401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19228","created_at":"2026-07-22T01:24:15.424401+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3T4YEYY7QLA","created_at":"2026-07-22T01:24:15.424401+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3T4YEYY7QLA4LTM","created_at":"2026-07-22T01:24:15.424401+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3T4YEYY","created_at":"2026-07-22T01:24:15.424401+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/V3T4YEYY7QLA4LTMTMO3XO6JGD","json":"https://pith.science/pith/V3T4YEYY7QLA4LTMTMO3XO6JGD.json","graph_json":"https://pith.science/api/pith-number/V3T4YEYY7QLA4LTMTMO3XO6JGD/graph.json","events_json":"https://pith.science/api/pith-number/V3T4YEYY7QLA4LTMTMO3XO6JGD/events.json","paper":"https://pith.science/paper/V3T4YEYY"},"agent_actions":{"view_html":"https://pith.science/pith/V3T4YEYY7QLA4LTMTMO3XO6JGD","download_json":"https://pith.science/pith/V3T4YEYY7QLA4LTMTMO3XO6JGD.json","view_paper":"https://pith.science/paper/V3T4YEYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19228&json=true","fetch_graph":"https://pith.science/api/pith-number/V3T4YEYY7QLA4LTMTMO3XO6JGD/graph.json","fetch_events":"https://pith.science/api/pith-number/V3T4YEYY7QLA4LTMTMO3XO6JGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3T4YEYY7QLA4LTMTMO3XO6JGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3T4YEYY7QLA4LTMTMO3XO6JGD/action/storage_attestation","attest_author":"https://pith.science/pith/V3T4YEYY7QLA4LTMTMO3XO6JGD/action/author_attestation","sign_citation":"https://pith.science/pith/V3T4YEYY7QLA4LTMTMO3XO6JGD/action/citation_signature","submit_replication":"https://pith.science/pith/V3T4YEYY7QLA4LTMTMO3XO6JGD/action/replication_record"}},"created_at":"2026-07-22T01:24:15.424401+00:00","updated_at":"2026-07-22T01:24:15.424401+00:00"}