{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HNC3HSIVFBD5F3NWPCVXFI5TSU","short_pith_number":"pith:HNC3HSIV","schema_version":"1.0","canonical_sha256":"3b45b3c9152847d2edb678ab72a3b39501a71525cd5a2ce19d6c436945408376","source":{"kind":"arxiv","id":"2406.00830","version":2},"attestation_state":"computed","paper":{"title":"Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Hang Xu, Yang Cao, Yihan Zeng","submitted_at":"2024-06-02T18:32:37Z","abstract_excerpt":"Open-vocabulary 3D Object Detection (OV-3DDet) addresses the detection of objects from an arbitrary list of novel categories in 3D scenes, which remains a very challenging problem. In this work, we propose CoDAv2, a unified framework designed to innovatively tackle both the localization and classification of novel 3D objects, under the condition of limited base categories. For localization, the proposed 3D Novel Object Discovery (3D-NOD) strategy utilizes 3D geometries and 2D open-vocabulary semantic priors to discover pseudo labels for novel objects during training. 3D-NOD is further extended"},"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":"2406.00830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-02T18:32:37Z","cross_cats_sorted":[],"title_canon_sha256":"d824c2f18a2b0d6f5e73910bc31b15e7de575a88717b5bfc720c3cc15084836b","abstract_canon_sha256":"bbe8dcb048680471748b415027985b7233f6faf448907fd33b847acbbc87264a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:11.942496Z","signature_b64":"uVw5ZzoorsykASrziKxg0LAkqnze4b1O5QDm7c3zzRsbf3cayXxzM1TM7lp4upkQQn5A6mv7c1bMfQaMpLrBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b45b3c9152847d2edb678ab72a3b39501a71525cd5a2ce19d6c436945408376","last_reissued_at":"2026-07-05T11:47:11.941992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:11.941992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Hang Xu, Yang Cao, Yihan Zeng","submitted_at":"2024-06-02T18:32:37Z","abstract_excerpt":"Open-vocabulary 3D Object Detection (OV-3DDet) addresses the detection of objects from an arbitrary list of novel categories in 3D scenes, which remains a very challenging problem. In this work, we propose CoDAv2, a unified framework designed to innovatively tackle both the localization and classification of novel 3D objects, under the condition of limited base categories. For localization, the proposed 3D Novel Object Discovery (3D-NOD) strategy utilizes 3D geometries and 2D open-vocabulary semantic priors to discover pseudo labels for novel objects during training. 3D-NOD is further extended"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00830","kind":"arxiv","version":2},"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/2406.00830/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":"2406.00830","created_at":"2026-07-05T11:47:11.942050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00830v2","created_at":"2026-07-05T11:47:11.942050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00830","created_at":"2026-07-05T11:47:11.942050+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNC3HSIVFBD5","created_at":"2026-07-05T11:47:11.942050+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNC3HSIVFBD5F3NW","created_at":"2026-07-05T11:47:11.942050+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNC3HSIV","created_at":"2026-07-05T11:47:11.942050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16812","citing_title":"Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU","json":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU.json","graph_json":"https://pith.science/api/pith-number/HNC3HSIVFBD5F3NWPCVXFI5TSU/graph.json","events_json":"https://pith.science/api/pith-number/HNC3HSIVFBD5F3NWPCVXFI5TSU/events.json","paper":"https://pith.science/paper/HNC3HSIV"},"agent_actions":{"view_html":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU","download_json":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU.json","view_paper":"https://pith.science/paper/HNC3HSIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00830&json=true","fetch_graph":"https://pith.science/api/pith-number/HNC3HSIVFBD5F3NWPCVXFI5TSU/graph.json","fetch_events":"https://pith.science/api/pith-number/HNC3HSIVFBD5F3NWPCVXFI5TSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU/action/storage_attestation","attest_author":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU/action/author_attestation","sign_citation":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU/action/citation_signature","submit_replication":"https://pith.science/pith/HNC3HSIVFBD5F3NWPCVXFI5TSU/action/replication_record"}},"created_at":"2026-07-05T11:47:11.942050+00:00","updated_at":"2026-07-05T11:47:11.942050+00:00"}