{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HUVIGOD3IXTK72VGLTGIVTMTBK","short_pith_number":"pith:HUVIGOD3","schema_version":"1.0","canonical_sha256":"3d2a83387b45e6afeaa65ccc8acd930a99689d3d50d796019e901456dcfdc67b","source":{"kind":"arxiv","id":"2608.02980","version":1},"attestation_state":"computed","paper":{"title":"Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush Jain, Katerina Fragkiadaki, Lucy Lin, Yifan Liu","submitted_at":"2026-08-04T00:32:09Z","abstract_excerpt":"Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to frame-centric tokenization and limited context windows. 3D geometry provides a natural compression mechanism for visual streams: depth and camera pose enable observations from multiple views and time steps to be fused into a persistent, world-aligned representation. While recent 3D LMMs leverage geometry-aware representations to improve spatial reasoning, they continue to lag behind specialist 3D perception systems on grounding and segmentation "},"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":"2608.02980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T00:32:09Z","cross_cats_sorted":[],"title_canon_sha256":"41bd64fc927c9b10536d599b925101acf9bfedee2cceb24ed0ab27e76fa3a6df","abstract_canon_sha256":"f23c12303f5e61ebc4aa14e3856af878bb27ba3be6f413efd6d0542b08a8ef73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:44:19.025650Z","signature_b64":"4Ims8JTZvnzmQaMbL/0c9BtclJkUT7XIbk7DFRT98n8X+JPOyzJg/HubpkbmlxK0mFrVzcMjCQI7i0PWlVFmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2a83387b45e6afeaa65ccc8acd930a99689d3d50d796019e901456dcfdc67b","last_reissued_at":"2026-08-05T00:44:19.023059Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:44:19.023059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush Jain, Katerina Fragkiadaki, Lucy Lin, Yifan Liu","submitted_at":"2026-08-04T00:32:09Z","abstract_excerpt":"Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to frame-centric tokenization and limited context windows. 3D geometry provides a natural compression mechanism for visual streams: depth and camera pose enable observations from multiple views and time steps to be fused into a persistent, world-aligned representation. While recent 3D LMMs leverage geometry-aware representations to improve spatial reasoning, they continue to lag behind specialist 3D perception systems on grounding and segmentation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02980","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/2608.02980/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":"2608.02980","created_at":"2026-08-05T00:44:19.023984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02980v1","created_at":"2026-08-05T00:44:19.023984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02980","created_at":"2026-08-05T00:44:19.023984+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUVIGOD3IXTK","created_at":"2026-08-05T00:44:19.023984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUVIGOD3IXTK72VG","created_at":"2026-08-05T00:44:19.023984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUVIGOD3","created_at":"2026-08-05T00:44:19.023984+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/HUVIGOD3IXTK72VGLTGIVTMTBK","json":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK.json","graph_json":"https://pith.science/api/pith-number/HUVIGOD3IXTK72VGLTGIVTMTBK/graph.json","events_json":"https://pith.science/api/pith-number/HUVIGOD3IXTK72VGLTGIVTMTBK/events.json","paper":"https://pith.science/paper/HUVIGOD3"},"agent_actions":{"view_html":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK","download_json":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK.json","view_paper":"https://pith.science/paper/HUVIGOD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02980&json=true","fetch_graph":"https://pith.science/api/pith-number/HUVIGOD3IXTK72VGLTGIVTMTBK/graph.json","fetch_events":"https://pith.science/api/pith-number/HUVIGOD3IXTK72VGLTGIVTMTBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/action/storage_attestation","attest_author":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/action/author_attestation","sign_citation":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/action/citation_signature","submit_replication":"https://pith.science/pith/HUVIGOD3IXTK72VGLTGIVTMTBK/action/replication_record"}},"created_at":"2026-08-05T00:44:19.023984+00:00","updated_at":"2026-08-05T00:44:19.023984+00:00"}