{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VQ3ITQONBAXQOGNQRDV3ZO3TYR","short_pith_number":"pith:VQ3ITQON","schema_version":"1.0","canonical_sha256":"ac3689c1cd082f0719b088ebbcbb73c44a4fa2efabcbe57a9d853f1f6210fd68","source":{"kind":"arxiv","id":"2309.04561","version":3},"attestation_state":"computed","paper":{"title":"Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Christos Sakaridis, Luc Van Gool, Ozan Unal, Suman Saha","submitted_at":"2023-09-08T19:27:01Z","abstract_excerpt":"3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autonomous indoor robotics to AR/VR, the task has recently risen in popularity. A common formulation to tackle 3D visual grounding is grounding-by-detection, where localization is done via bounding boxes. However, for real-life applications that require physical interactions, a bounding box insufficiently describes the geometry of an object. We therefore tackle the problem of dense 3D visual grounding, i.e. referral-based "},"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":"2309.04561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T19:27:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6b446c2868c779e9b5492e2394ac0c5da4ccb25bc3bb6d0493532bfc0a30421c","abstract_canon_sha256":"2e70d3c2dd045586148631b3eb9a53fcbc65d7dc3319378dd2d0d419dc9d790f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:09.665786Z","signature_b64":"uYyZUg+Cu6/MWcRscFH7yaqvLEsmoZw7aew19GTeR1NQmjjo8tgnRaqV+Xhe5dSdhCamcy2DnbUMSYlGVqwlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac3689c1cd082f0719b088ebbcbb73c44a4fa2efabcbe57a9d853f1f6210fd68","last_reissued_at":"2026-07-05T08:44:09.665345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:09.665345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Christos Sakaridis, Luc Van Gool, Ozan Unal, Suman Saha","submitted_at":"2023-09-08T19:27:01Z","abstract_excerpt":"3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autonomous indoor robotics to AR/VR, the task has recently risen in popularity. A common formulation to tackle 3D visual grounding is grounding-by-detection, where localization is done via bounding boxes. However, for real-life applications that require physical interactions, a bounding box insufficiently describes the geometry of an object. We therefore tackle the problem of dense 3D visual grounding, i.e. referral-based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04561","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/2309.04561/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":"2309.04561","created_at":"2026-07-05T08:44:09.665405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04561v3","created_at":"2026-07-05T08:44:09.665405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04561","created_at":"2026-07-05T08:44:09.665405+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQ3ITQONBAXQ","created_at":"2026-07-05T08:44:09.665405+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQ3ITQONBAXQOGNQ","created_at":"2026-07-05T08:44:09.665405+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQ3ITQON","created_at":"2026-07-05T08:44:09.665405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR","json":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR.json","graph_json":"https://pith.science/api/pith-number/VQ3ITQONBAXQOGNQRDV3ZO3TYR/graph.json","events_json":"https://pith.science/api/pith-number/VQ3ITQONBAXQOGNQRDV3ZO3TYR/events.json","paper":"https://pith.science/paper/VQ3ITQON"},"agent_actions":{"view_html":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR","download_json":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR.json","view_paper":"https://pith.science/paper/VQ3ITQON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04561&json=true","fetch_graph":"https://pith.science/api/pith-number/VQ3ITQONBAXQOGNQRDV3ZO3TYR/graph.json","fetch_events":"https://pith.science/api/pith-number/VQ3ITQONBAXQOGNQRDV3ZO3TYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR/action/storage_attestation","attest_author":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR/action/author_attestation","sign_citation":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR/action/citation_signature","submit_replication":"https://pith.science/pith/VQ3ITQONBAXQOGNQRDV3ZO3TYR/action/replication_record"}},"created_at":"2026-07-05T08:44:09.665405+00:00","updated_at":"2026-07-05T08:44:09.665405+00:00"}