{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VQ3ITQONBAXQOGNQRDV3ZO3TYR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2e70d3c2dd045586148631b3eb9a53fcbc65d7dc3319378dd2d0d419dc9d790f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T19:27:01Z","title_canon_sha256":"6b446c2868c779e9b5492e2394ac0c5da4ccb25bc3bb6d0493532bfc0a30421c"},"schema_version":"1.0","source":{"id":"2309.04561","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04561","created_at":"2026-07-05T08:44:09Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04561v3","created_at":"2026-07-05T08:44:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04561","created_at":"2026-07-05T08:44:09Z"},{"alias_kind":"pith_short_12","alias_value":"VQ3ITQONBAXQ","created_at":"2026-07-05T08:44:09Z"},{"alias_kind":"pith_short_16","alias_value":"VQ3ITQONBAXQOGNQ","created_at":"2026-07-05T08:44:09Z"},{"alias_kind":"pith_short_8","alias_value":"VQ3ITQON","created_at":"2026-07-05T08:44:09Z"}],"graph_snapshots":[{"event_id":"sha256:6dd2d9e369bb229b48c46c8c67388c118964d9c46077dc10dd55fe99a054de13","target":"graph","created_at":"2026-07-05T08:44:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.04561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Christos Sakaridis, Luc Van Gool, Ozan Unal, Suman Saha","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T19:27:01Z","title":"Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04561","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5bce1af61300c4e124250c71221168bf4c41f977d7ab2c36f363c63a38326200","target":"record","created_at":"2026-07-05T08:44:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2e70d3c2dd045586148631b3eb9a53fcbc65d7dc3319378dd2d0d419dc9d790f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T19:27:01Z","title_canon_sha256":"6b446c2868c779e9b5492e2394ac0c5da4ccb25bc3bb6d0493532bfc0a30421c"},"schema_version":"1.0","source":{"id":"2309.04561","kind":"arxiv","version":3}},"canonical_sha256":"ac3689c1cd082f0719b088ebbcbb73c44a4fa2efabcbe57a9d853f1f6210fd68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac3689c1cd082f0719b088ebbcbb73c44a4fa2efabcbe57a9d853f1f6210fd68","first_computed_at":"2026-07-05T08:44:09.665345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:09.665345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uYyZUg+Cu6/MWcRscFH7yaqvLEsmoZw7aew19GTeR1NQmjjo8tgnRaqV+Xhe5dSdhCamcy2DnbUMSYlGVqwlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:09.665786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04561","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bce1af61300c4e124250c71221168bf4c41f977d7ab2c36f363c63a38326200","sha256:6dd2d9e369bb229b48c46c8c67388c118964d9c46077dc10dd55fe99a054de13"],"state_sha256":"f5467308120cbb91a1d668a52644b7bf8b8ffead874b0d3aff585800814d351f"}