{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TNTWXOZJN73ZNBGISOPRKXIUVQ","short_pith_number":"pith:TNTWXOZJ","schema_version":"1.0","canonical_sha256":"9b676bbb296ff79684c8939f155d14ac1b5818526d31ccf306bbdd92144fd924","source":{"kind":"arxiv","id":"2210.03925","version":1},"attestation_state":"computed","paper":{"title":"Contextual Modeling for 3D Dense Captioning on Point Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Lin Ma, Long Xu, Yufeng Zhong","submitted_at":"2022-10-08T05:33:00Z","abstract_excerpt":"3D dense captioning, as an emerging vision-language task, aims to identify and locate each object from a set of point clouds and generate a distinctive natural language sentence for describing each located object. However, the existing methods mainly focus on mining inter-object relationship, while ignoring contextual information, especially the non-object details and background environment within the point clouds, thus leading to low-quality descriptions, such as inaccurate relative position information. In this paper, we make the first attempt to utilize the point clouds clustering features "},"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":"2210.03925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-08T05:33:00Z","cross_cats_sorted":[],"title_canon_sha256":"0765c6bf3e2b44ba32f45660b0a386bd3032307e925ae4c9f22da527625d3ae3","abstract_canon_sha256":"550a792b33603b8915a7101e15f3118775644ffcda8a41b09ba1f9cbd39e9852"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:33.810042Z","signature_b64":"+AQ8jzYda4HPjWPDvhAxWdLF/IafV8qa0rcM/g4EArhTWbMzcGu4CT6q8FqoSa5TwKKV2ibC/Ub0aqDqRiRPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b676bbb296ff79684c8939f155d14ac1b5818526d31ccf306bbdd92144fd924","last_reissued_at":"2026-07-05T05:04:33.809566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:33.809566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Modeling for 3D Dense Captioning on Point Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Lin Ma, Long Xu, Yufeng Zhong","submitted_at":"2022-10-08T05:33:00Z","abstract_excerpt":"3D dense captioning, as an emerging vision-language task, aims to identify and locate each object from a set of point clouds and generate a distinctive natural language sentence for describing each located object. However, the existing methods mainly focus on mining inter-object relationship, while ignoring contextual information, especially the non-object details and background environment within the point clouds, thus leading to low-quality descriptions, such as inaccurate relative position information. In this paper, we make the first attempt to utilize the point clouds clustering features "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03925","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/2210.03925/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":"2210.03925","created_at":"2026-07-05T05:04:33.809623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03925v1","created_at":"2026-07-05T05:04:33.809623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03925","created_at":"2026-07-05T05:04:33.809623+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNTWXOZJN73Z","created_at":"2026-07-05T05:04:33.809623+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNTWXOZJN73ZNBGI","created_at":"2026-07-05T05:04:33.809623+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNTWXOZJ","created_at":"2026-07-05T05:04:33.809623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08808","citing_title":"Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ","json":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ.json","graph_json":"https://pith.science/api/pith-number/TNTWXOZJN73ZNBGISOPRKXIUVQ/graph.json","events_json":"https://pith.science/api/pith-number/TNTWXOZJN73ZNBGISOPRKXIUVQ/events.json","paper":"https://pith.science/paper/TNTWXOZJ"},"agent_actions":{"view_html":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ","download_json":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ.json","view_paper":"https://pith.science/paper/TNTWXOZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03925&json=true","fetch_graph":"https://pith.science/api/pith-number/TNTWXOZJN73ZNBGISOPRKXIUVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TNTWXOZJN73ZNBGISOPRKXIUVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ/action/storage_attestation","attest_author":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ/action/author_attestation","sign_citation":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ/action/citation_signature","submit_replication":"https://pith.science/pith/TNTWXOZJN73ZNBGISOPRKXIUVQ/action/replication_record"}},"created_at":"2026-07-05T05:04:33.809623+00:00","updated_at":"2026-07-05T05:04:33.809623+00:00"}