{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4PITNMTI5WXVNNEOOSVYYVFVXJ","short_pith_number":"pith:4PITNMTI","schema_version":"1.0","canonical_sha256":"e3d136b268edaf56b48e74ab8c54b5ba4185cd822b8639a69dda097d375cc5ae","source":{"kind":"arxiv","id":"2505.04965","version":1},"attestation_state":"computed","paper":{"title":"DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Hao Shi, Henry Zheng, Qihang Peng, Rui Huang, Yepeng Weng, Yong Xien Chng, Zhongchao Shi","submitted_at":"2025-05-08T05:49:06Z","abstract_excerpt":"Enabling intelligent agents to comprehend and interact with 3D environments through natural language is crucial for advancing robotics and human-computer interaction. A fundamental task in this field is ego-centric 3D visual grounding, where agents locate target objects in real-world 3D spaces based on verbal descriptions. However, this task faces two significant challenges: (1) loss of fine-grained visual semantics due to sparse fusion of point clouds with ego-centric multi-view images, (2) limited textual semantic context due to arbitrary language descriptions. We propose DenseGrounding, a n"},"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":"2505.04965","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T05:49:06Z","cross_cats_sorted":[],"title_canon_sha256":"5a9a96ebcdf5afe38a7ba90006083d323bcf8080feeb1eed429a09bcb338eec5","abstract_canon_sha256":"f5859d79eff0cfd8d53ce1b7e033144ca654fa6327427b8d78eebe4d54e8cf4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:16.779683Z","signature_b64":"2vuspAIWwbFw55CqJ1J7o1ngZTsZjgGMYIcgMFN1sC8iQ1gfhXc0YMt/EVGwW6R5cFzAxRyy7Nmuq+6t+WvhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3d136b268edaf56b48e74ab8c54b5ba4185cd822b8639a69dda097d375cc5ae","last_reissued_at":"2026-07-05T11:00:16.779141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:16.779141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Hao Shi, Henry Zheng, Qihang Peng, Rui Huang, Yepeng Weng, Yong Xien Chng, Zhongchao Shi","submitted_at":"2025-05-08T05:49:06Z","abstract_excerpt":"Enabling intelligent agents to comprehend and interact with 3D environments through natural language is crucial for advancing robotics and human-computer interaction. A fundamental task in this field is ego-centric 3D visual grounding, where agents locate target objects in real-world 3D spaces based on verbal descriptions. However, this task faces two significant challenges: (1) loss of fine-grained visual semantics due to sparse fusion of point clouds with ego-centric multi-view images, (2) limited textual semantic context due to arbitrary language descriptions. We propose DenseGrounding, a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04965","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/2505.04965/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":"2505.04965","created_at":"2026-07-05T11:00:16.779199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04965v1","created_at":"2026-07-05T11:00:16.779199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04965","created_at":"2026-07-05T11:00:16.779199+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PITNMTI5WXV","created_at":"2026-07-05T11:00:16.779199+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PITNMTI5WXVNNEO","created_at":"2026-07-05T11:00:16.779199+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PITNMTI","created_at":"2026-07-05T11:00:16.779199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10925","citing_title":"PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ","json":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ.json","graph_json":"https://pith.science/api/pith-number/4PITNMTI5WXVNNEOOSVYYVFVXJ/graph.json","events_json":"https://pith.science/api/pith-number/4PITNMTI5WXVNNEOOSVYYVFVXJ/events.json","paper":"https://pith.science/paper/4PITNMTI"},"agent_actions":{"view_html":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ","download_json":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ.json","view_paper":"https://pith.science/paper/4PITNMTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04965&json=true","fetch_graph":"https://pith.science/api/pith-number/4PITNMTI5WXVNNEOOSVYYVFVXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4PITNMTI5WXVNNEOOSVYYVFVXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ/action/storage_attestation","attest_author":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ/action/author_attestation","sign_citation":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ/action/citation_signature","submit_replication":"https://pith.science/pith/4PITNMTI5WXVNNEOOSVYYVFVXJ/action/replication_record"}},"created_at":"2026-07-05T11:00:16.779199+00:00","updated_at":"2026-07-05T11:00:16.779199+00:00"}