{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3OGRSPX3UKEYPDFJAB5PNXUOMR","short_pith_number":"pith:3OGRSPX3","schema_version":"1.0","canonical_sha256":"db8d193efba289878ca9007af6de8e645e6a91e7c870037e352c74970af66a2a","source":{"kind":"arxiv","id":"2505.20639","version":1},"attestation_state":"computed","paper":{"title":"Open-Det: An Efficient Learning Framework for Open-Ended Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongmei Jiang, Guiping Cao, Jianguo Zhang, Tao Wang, Wenjian Huang, Xiangyuan Lan","submitted_at":"2025-05-27T02:33:10Z","abstract_excerpt":"Open-Ended object Detection (OED) is a novel and challenging task that detects objects and generates their category names in a free-form manner, without requiring additional vocabularies during inference. However, the existing OED models, such as GenerateU, require large-scale datasets for training, suffer from slow convergence, and exhibit limited performance. To address these issues, we present a novel and efficient Open-Det framework, consisting of four collaborative parts. Specifically, Open-Det accelerates model training in both the bounding box and object name generation process by recon"},"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":"2505.20639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T02:33:10Z","cross_cats_sorted":[],"title_canon_sha256":"b02dc929af46a23d8432fb41263745ae2efae7280655970e49c561a51f371472","abstract_canon_sha256":"d904e232d074d1a2f268ffe9ba556d4c2a128ba3cb515817d8be025abdc2f93e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:15.865032Z","signature_b64":"eVzp2IVQ7wri/37X0mEeJIyx9cjMFD0uFRWInkBBs2Pl5ZVLQ+eSAo7H1Gu53hqF40jc2ZR/rPpY/r5UNEVMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db8d193efba289878ca9007af6de8e645e6a91e7c870037e352c74970af66a2a","last_reissued_at":"2026-07-05T11:10:15.864454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:15.864454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Det: An Efficient Learning Framework for Open-Ended Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongmei Jiang, Guiping Cao, Jianguo Zhang, Tao Wang, Wenjian Huang, Xiangyuan Lan","submitted_at":"2025-05-27T02:33:10Z","abstract_excerpt":"Open-Ended object Detection (OED) is a novel and challenging task that detects objects and generates their category names in a free-form manner, without requiring additional vocabularies during inference. However, the existing OED models, such as GenerateU, require large-scale datasets for training, suffer from slow convergence, and exhibit limited performance. To address these issues, we present a novel and efficient Open-Det framework, consisting of four collaborative parts. Specifically, Open-Det accelerates model training in both the bounding box and object name generation process by recon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20639","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/2505.20639/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":"2505.20639","created_at":"2026-07-05T11:10:15.864520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20639v1","created_at":"2026-07-05T11:10:15.864520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20639","created_at":"2026-07-05T11:10:15.864520+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OGRSPX3UKEY","created_at":"2026-07-05T11:10:15.864520+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OGRSPX3UKEYPDFJ","created_at":"2026-07-05T11:10:15.864520+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OGRSPX3","created_at":"2026-07-05T11:10:15.864520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR","json":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR.json","graph_json":"https://pith.science/api/pith-number/3OGRSPX3UKEYPDFJAB5PNXUOMR/graph.json","events_json":"https://pith.science/api/pith-number/3OGRSPX3UKEYPDFJAB5PNXUOMR/events.json","paper":"https://pith.science/paper/3OGRSPX3"},"agent_actions":{"view_html":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR","download_json":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR.json","view_paper":"https://pith.science/paper/3OGRSPX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20639&json=true","fetch_graph":"https://pith.science/api/pith-number/3OGRSPX3UKEYPDFJAB5PNXUOMR/graph.json","fetch_events":"https://pith.science/api/pith-number/3OGRSPX3UKEYPDFJAB5PNXUOMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR/action/storage_attestation","attest_author":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR/action/author_attestation","sign_citation":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR/action/citation_signature","submit_replication":"https://pith.science/pith/3OGRSPX3UKEYPDFJAB5PNXUOMR/action/replication_record"}},"created_at":"2026-07-05T11:10:15.864520+00:00","updated_at":"2026-07-05T11:10:15.864520+00:00"}