{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PBAVIODRCB2A2534HGUNMOUUGR","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":"36bb5b5e46de7e87c656dcc3907cb01946de5aac250e675f629e01c6e7ae1605","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T19:00:06Z","title_canon_sha256":"8d3563d9c171948287ca1abfc6dde03cb4c4ef02fb9d0cb25fa154d4564b9b40"},"schema_version":"1.0","source":{"id":"2112.01551","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01551","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01551v2","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01551","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"PBAVIODRCB2A","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"pith_short_16","alias_value":"PBAVIODRCB2A2534","created_at":"2026-07-05T04:42:32Z"},{"alias_kind":"pith_short_8","alias_value":"PBAVIODR","created_at":"2026-07-05T04:42:32Z"}],"graph_snapshots":[{"event_id":"sha256:e041489ac73a68a3ec0ece9b84423a962237ae02f9f8069d0e5fb2818ade5af4","target":"graph","created_at":"2026-07-05T04:42:32Z","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/2112.01551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies on dense captioning and visual grounding in 3D have achieved impressive results. Despite developments in both areas, the limited amount of available 3D vision-language data causes overfitting issues for 3D visual grounding and 3D dense captioning methods. Also, how to discriminatively describe objects in complex 3D environments is not fully studied yet. To address these challenges, we present D3Net, an end-to-end neural speaker-listener architecture that can detect, describe and discriminate. Our D3Net unifies dense captioning and visual grounding in 3D in a self-critical manner","authors_text":"Angel X. Chang, Dave Zhenyu Chen, Matthias Nie{\\ss}ner, Qirui Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T19:00:06Z","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01551","kind":"arxiv","version":2},"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":"sha256:798ddd4736ab4cc8b47e0643605d37829f85aba595bb07b3d5d7eeae347ce5ef","target":"record","created_at":"2026-07-05T04:42:32Z","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":"36bb5b5e46de7e87c656dcc3907cb01946de5aac250e675f629e01c6e7ae1605","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T19:00:06Z","title_canon_sha256":"8d3563d9c171948287ca1abfc6dde03cb4c4ef02fb9d0cb25fa154d4564b9b40"},"schema_version":"1.0","source":{"id":"2112.01551","kind":"arxiv","version":2}},"canonical_sha256":"784154387110740d777c39a8d63a94345a856327af56d800c2cc7936e383e65f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"784154387110740d777c39a8d63a94345a856327af56d800c2cc7936e383e65f","first_computed_at":"2026-07-05T04:42:32.230893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:32.230893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zQZlnBIoiAgKnEikMYZTEWNurmOGfErmuVUOOFmlyQuBD+vFuIMvj9mBdtyk7Elb2y9L5CqrqjFWsJIeA0n/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:32.231375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01551","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:798ddd4736ab4cc8b47e0643605d37829f85aba595bb07b3d5d7eeae347ce5ef","sha256:e041489ac73a68a3ec0ece9b84423a962237ae02f9f8069d0e5fb2818ade5af4"],"state_sha256":"95c402462435c03c160bd9619b44b1abb304fb8987648f11dc5d158480f3041a"}