{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AJGZ6V7SFKQTINPTRHMXAKCMYT","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":"ae4e3fccf6ad024076a496f260eb37bd99771c90386028213161fa74539e276a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T04:46:27Z","title_canon_sha256":"e09175c54877468e7ce98459893cc359fc33c076c9096147e0525a8fb4b93d3e"},"schema_version":"1.0","source":{"id":"2404.11064","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11064","created_at":"2026-07-05T09:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11064v3","created_at":"2026-07-05T09:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11064","created_at":"2026-07-05T09:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"AJGZ6V7SFKQT","created_at":"2026-07-05T09:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"AJGZ6V7SFKQTINPT","created_at":"2026-07-05T09:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"AJGZ6V7S","created_at":"2026-07-05T09:50:46Z"}],"graph_snapshots":[{"event_id":"sha256:ab4d73533edbe940905205cf3c477f35c51f05b04c35baead698ef57bc898c24","target":"graph","created_at":"2026-07-05T09:50:46Z","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/2404.11064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships. Therefore, existing approaches adopt the two-stage \"detect-then-describe/discriminate\" pipeline, which relies heavily on the performance of the detector, resulting in suboptimal performance. Inspired by DETR, we propose a unified framework, 3DGCTR, to jointly solve these two distinct but closely related tasks in an end-to-end fashion. The key idea is to reconsider the prompt-based l","authors_text":"Fei Chao, Guannan Jiang, Haojia Lin, Jie Hu, Rongrong Ji, Songan Zhang, Xiawu Zheng, Yigeng Jiang, Yongdong Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T04:46:27Z","title":"Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11064","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:f0033409a1ba0f2e0906cd5ea26839c1555841b194fb1b58a6ca11fc1119f32a","target":"record","created_at":"2026-07-05T09:50:46Z","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":"ae4e3fccf6ad024076a496f260eb37bd99771c90386028213161fa74539e276a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T04:46:27Z","title_canon_sha256":"e09175c54877468e7ce98459893cc359fc33c076c9096147e0525a8fb4b93d3e"},"schema_version":"1.0","source":{"id":"2404.11064","kind":"arxiv","version":3}},"canonical_sha256":"024d9f57f22aa13435f389d970284cc4f38484ed0bf4f8e80172f03479ebcef3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"024d9f57f22aa13435f389d970284cc4f38484ed0bf4f8e80172f03479ebcef3","first_computed_at":"2026-07-05T09:50:46.932971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:46.932971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nj1DwQB3mt0sS9g+h40/DZVt1N5LlD23MZfNGK7gat4rNLujwOnInMJP05KaCYH/2GO45F+Ox7UEjpFVXgxBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:46.933464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11064","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0033409a1ba0f2e0906cd5ea26839c1555841b194fb1b58a6ca11fc1119f32a","sha256:ab4d73533edbe940905205cf3c477f35c51f05b04c35baead698ef57bc898c24"],"state_sha256":"31230364b9d0f4a8d99028769778749ce0062b38946716c6e4734e4ce3ce64f8"}