{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AIVOO2YG27KXAE5UIFM7YEVBN4","short_pith_number":"pith:AIVOO2YG","schema_version":"1.0","canonical_sha256":"022ae76b06d7d57013b44159fc12a16f2c48c7112ef31d442da93ddaee2900d4","source":{"kind":"arxiv","id":"2505.04058","version":3},"attestation_state":"computed","paper":{"title":"LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Xiao, Guocan Zhao, Hongbin Xu, Wenxiong Kang","submitted_at":"2025-05-07T02:02:15Z","abstract_excerpt":"3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the described spatial relationships. Current methods attempt to achieve cross-modal understanding in complex scenes via a target-centered learning mechanism, ignoring the modeling of referred objects. We propose a novel 3D visual grounding framework that constructs language-guided scene graphs with referred object discrimination to improve relational perception. The"},"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":"2505.04058","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T02:02:15Z","cross_cats_sorted":[],"title_canon_sha256":"a8cabd0bcb7c5505f1adbb9cb2af4008bc34ca23f5f54ec28c0779253426fe0b","abstract_canon_sha256":"15fe4b82d54bcd7ecb3a4d6c9af2a19c87f8a83bd82e70e43b43b37503a4d6ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:11.883365Z","signature_b64":"+dt+Xpa/5kFFDD4mMoNNjLs6yFqOfXSgR0g+PyxrxJ93ynlDXRMgnL0gZaauXiv1Lk8vByoAk6NWlL70e4HUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"022ae76b06d7d57013b44159fc12a16f2c48c7112ef31d442da93ddaee2900d4","last_reissued_at":"2026-07-05T11:54:11.882938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:11.882938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Xiao, Guocan Zhao, Hongbin Xu, Wenxiong Kang","submitted_at":"2025-05-07T02:02:15Z","abstract_excerpt":"3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the described spatial relationships. Current methods attempt to achieve cross-modal understanding in complex scenes via a target-centered learning mechanism, ignoring the modeling of referred objects. We propose a novel 3D visual grounding framework that constructs language-guided scene graphs with referred object discrimination to improve relational perception. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04058","kind":"arxiv","version":3},"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/2505.04058/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":"2505.04058","created_at":"2026-07-05T11:54:11.882995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04058v3","created_at":"2026-07-05T11:54:11.882995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04058","created_at":"2026-07-05T11:54:11.882995+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIVOO2YG27KX","created_at":"2026-07-05T11:54:11.882995+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIVOO2YG27KXAE5U","created_at":"2026-07-05T11:54:11.882995+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIVOO2YG","created_at":"2026-07-05T11:54:11.882995+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/AIVOO2YG27KXAE5UIFM7YEVBN4","json":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4.json","graph_json":"https://pith.science/api/pith-number/AIVOO2YG27KXAE5UIFM7YEVBN4/graph.json","events_json":"https://pith.science/api/pith-number/AIVOO2YG27KXAE5UIFM7YEVBN4/events.json","paper":"https://pith.science/paper/AIVOO2YG"},"agent_actions":{"view_html":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4","download_json":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4.json","view_paper":"https://pith.science/paper/AIVOO2YG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04058&json=true","fetch_graph":"https://pith.science/api/pith-number/AIVOO2YG27KXAE5UIFM7YEVBN4/graph.json","fetch_events":"https://pith.science/api/pith-number/AIVOO2YG27KXAE5UIFM7YEVBN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/action/storage_attestation","attest_author":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/action/author_attestation","sign_citation":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/action/citation_signature","submit_replication":"https://pith.science/pith/AIVOO2YG27KXAE5UIFM7YEVBN4/action/replication_record"}},"created_at":"2026-07-05T11:54:11.882995+00:00","updated_at":"2026-07-05T11:54:11.882995+00:00"}