{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TRGU3JSOXSLPTD4EO4ZWA3SG6K","short_pith_number":"pith:TRGU3JSO","schema_version":"1.0","canonical_sha256":"9c4d4da64ebc96f98f847733606e46f2b292410a720d5f078591e2482874b4fb","source":{"kind":"arxiv","id":"2304.03752","version":2},"attestation_state":"computed","paper":{"title":"V3Det: Vast Vocabulary Visual Detection Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Dahua Lin, Jiaqi Wang, Pan Zhang, Tao Chu, Tong Wu, Yuhang Cao, Yujie Zhou","submitted_at":"2023-04-07T17:45:35Z","abstract_excerpt":"Recent advances in detecting arbitrary objects in the real world are trained and evaluated on object detection datasets with a relatively restricted vocabulary. To facilitate the development of more general visual object detection, we propose V3Det, a vast vocabulary visual detection dataset with precisely annotated bounding boxes on massive images. V3Det has several appealing properties: 1) Vast Vocabulary: It contains bounding boxes of objects from 13,204 categories on real-world images, which is 10 times larger than the existing large vocabulary object detection dataset, e.g., LVIS. 2) Hier"},"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":"2304.03752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T17:45:35Z","cross_cats_sorted":[],"title_canon_sha256":"4ff09948514176d7d7c1f7ba9f2d2a86fc9a977734f1f42f5f119b8ed84038d2","abstract_canon_sha256":"462aed6697e2caa7278b57a16c9be6ca2b24ddc2161c06788bd28a05da877ef1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:22.404993Z","signature_b64":"58EmkzmbXAT7YQEXEu5kfJtK5zYKv5eU8oX4HM4+bjZ8x0Jz58R8/s0zCYcgsFJkMW4RYxRgb1f4vTMmGOWyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c4d4da64ebc96f98f847733606e46f2b292410a720d5f078591e2482874b4fb","last_reissued_at":"2026-07-05T06:57:22.404636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:22.404636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V3Det: Vast Vocabulary Visual Detection Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Dahua Lin, Jiaqi Wang, Pan Zhang, Tao Chu, Tong Wu, Yuhang Cao, Yujie Zhou","submitted_at":"2023-04-07T17:45:35Z","abstract_excerpt":"Recent advances in detecting arbitrary objects in the real world are trained and evaluated on object detection datasets with a relatively restricted vocabulary. To facilitate the development of more general visual object detection, we propose V3Det, a vast vocabulary visual detection dataset with precisely annotated bounding boxes on massive images. V3Det has several appealing properties: 1) Vast Vocabulary: It contains bounding boxes of objects from 13,204 categories on real-world images, which is 10 times larger than the existing large vocabulary object detection dataset, e.g., LVIS. 2) Hier"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03752","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/2304.03752/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":"2304.03752","created_at":"2026-07-05T06:57:22.404689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03752v2","created_at":"2026-07-05T06:57:22.404689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03752","created_at":"2026-07-05T06:57:22.404689+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRGU3JSOXSLP","created_at":"2026-07-05T06:57:22.404689+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRGU3JSOXSLPTD4E","created_at":"2026-07-05T06:57:22.404689+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRGU3JSO","created_at":"2026-07-05T06:57:22.404689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08626","citing_title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K","json":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K.json","graph_json":"https://pith.science/api/pith-number/TRGU3JSOXSLPTD4EO4ZWA3SG6K/graph.json","events_json":"https://pith.science/api/pith-number/TRGU3JSOXSLPTD4EO4ZWA3SG6K/events.json","paper":"https://pith.science/paper/TRGU3JSO"},"agent_actions":{"view_html":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K","download_json":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K.json","view_paper":"https://pith.science/paper/TRGU3JSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03752&json=true","fetch_graph":"https://pith.science/api/pith-number/TRGU3JSOXSLPTD4EO4ZWA3SG6K/graph.json","fetch_events":"https://pith.science/api/pith-number/TRGU3JSOXSLPTD4EO4ZWA3SG6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K/action/storage_attestation","attest_author":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K/action/author_attestation","sign_citation":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K/action/citation_signature","submit_replication":"https://pith.science/pith/TRGU3JSOXSLPTD4EO4ZWA3SG6K/action/replication_record"}},"created_at":"2026-07-05T06:57:22.404689+00:00","updated_at":"2026-07-05T06:57:22.404689+00:00"}