{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MUIOCX3XPJK5BZH65ZFCOWXBIQ","short_pith_number":"pith:MUIOCX3X","schema_version":"1.0","canonical_sha256":"6510e15f777a55d0e4feee4a275ae1440b8450044ce24e109f0588cf7aa5b0f0","source":{"kind":"arxiv","id":"2508.20758","version":1},"attestation_state":"computed","paper":{"title":"SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiawen Lin, Shiran Bian, Wenbin Tan, Yachao Zhang, Yanyun Qu, Yihang Zhu, Yuan Xie","submitted_at":"2025-08-28T13:15:37Z","abstract_excerpt":"3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, zero-shot 3DVG holds greater promise for real-world applications since eliminating scene-specific training requirements. However, existing zero-shot methods face challenges of spatial-limited reasoning due to reliance on single-view localization, and contextual omissions or detail degradation. To address these issues, we propose SeqVLM, a novel zero-shot 3DVG framework that leverages multi-view real-world scene images"},"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":"2508.20758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T13:15:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea3c4d170d235bcc69c91a52d4a13509fafe2d99cbdea5a94c3dad8f8723ba2d","abstract_canon_sha256":"8f677cc70dc2847af1b06d988c486b6899c6a081ab6b66745f67b9355e615dde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:10.247398Z","signature_b64":"eYJR84zSktoYsWKLSZvSnI0H2WyzkIgmsmM3AXxCfFCETcbhSVidxc9L14Ux9PnZInAQQafEmsZ9eHUPvgKhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6510e15f777a55d0e4feee4a275ae1440b8450044ce24e109f0588cf7aa5b0f0","last_reissued_at":"2026-07-05T12:01:10.246786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:10.246786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiawen Lin, Shiran Bian, Wenbin Tan, Yachao Zhang, Yanyun Qu, Yihang Zhu, Yuan Xie","submitted_at":"2025-08-28T13:15:37Z","abstract_excerpt":"3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, zero-shot 3DVG holds greater promise for real-world applications since eliminating scene-specific training requirements. However, existing zero-shot methods face challenges of spatial-limited reasoning due to reliance on single-view localization, and contextual omissions or detail degradation. To address these issues, we propose SeqVLM, a novel zero-shot 3DVG framework that leverages multi-view real-world scene images"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20758","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/2508.20758/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":"2508.20758","created_at":"2026-07-05T12:01:10.246848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20758v1","created_at":"2026-07-05T12:01:10.246848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20758","created_at":"2026-07-05T12:01:10.246848+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUIOCX3XPJK5","created_at":"2026-07-05T12:01:10.246848+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUIOCX3XPJK5BZH6","created_at":"2026-07-05T12:01:10.246848+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUIOCX3X","created_at":"2026-07-05T12:01:10.246848+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/MUIOCX3XPJK5BZH65ZFCOWXBIQ","json":"https://pith.science/pith/MUIOCX3XPJK5BZH65ZFCOWXBIQ.json","graph_json":"https://pith.science/api/pith-number/MUIOCX3XPJK5BZH65ZFCOWXBIQ/graph.json","events_json":"https://pith.science/api/pith-number/MUIOCX3XPJK5BZH65ZFCOWXBIQ/events.json","paper":"https://pith.science/paper/MUIOCX3X"},"agent_actions":{"view_html":"https://pith.science/pith/MUIOCX3XPJK5BZH65ZFCOWXBIQ","download_json":"https://pith.science/pith/MUIOCX3XPJK5BZH65ZFCOWXBIQ.json","view_paper":"https://pith.science/paper/MUIOCX3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20758&json=true","fetch_graph":"https://pith.science/api/pith-number/MUIOCX3XPJK5BZH65ZFCOWXBIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MUIOCX3XPJK5BZH65ZFCOWXBIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUIOCX3XPJK5BZH65ZFCOWXBIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUIOCX3XPJK5BZH65ZFCOWXBIQ/action/storage_attestation","attest_author":"https://pith.science/pith/MUIOCX3XPJK5BZH65ZFCOWXBIQ/action/author_attestation","sign_citation":"https://pith.science/pith/MUIOCX3XPJK5BZH65ZFCOWXBIQ/action/citation_signature","submit_replication":"https://pith.science/pith/MUIOCX3XPJK5BZH65ZFCOWXBIQ/action/replication_record"}},"created_at":"2026-07-05T12:01:10.246848+00:00","updated_at":"2026-07-05T12:01:10.246848+00:00"}