{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:476RYVLUA6JDV4YZAKBNXKIRUZ","short_pith_number":"pith:476RYVLU","schema_version":"1.0","canonical_sha256":"e7fd1c557407923af3190282dba911a674e622308e464a4a6dbad5a19a3f537a","source":{"kind":"arxiv","id":"2412.09799","version":1},"attestation_state":"computed","paper":{"title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jian Jiang, Jianyue Ge, Jianzhong Chen, Li Yu, Mengdi Liu, Qibo Chen, Shuchang Li, Weizhong Jin, Xuanjiang Guo, Yuchao Yan","submitted_at":"2024-12-13T02:36:29Z","abstract_excerpt":"Recent research on universal object detection aims to introduce language in a SoTA closed-set detector and then generalize the open-set concepts by constructing large-scale (text-region) datasets for training. However, these methods face two main challenges: (i) how to efficiently use the prior information in the prompts to genericise objects and (ii) how to reduce alignment bias in the downstream tasks, both leading to sub-optimal performance in some scenarios beyond pre-training. To address these challenges, we propose a strong universal detection foundation model called CP-DETR, which is co"},"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":"2412.09799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T02:36:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"628432f46a67082c3aca3aa3b0215087a3f0fa91845dfc6a0506cec6c8e80d16","abstract_canon_sha256":"e76030670929447f1c3db125e955d8a8fa122ba70d6847bfb5208c6f8a3b8d74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:41.767372Z","signature_b64":"mEuSwmz91dxSKEnmv4Gws/X+5LoRkEodA3l2x0DHN8StydbCn0wgtM8VO0oI5B5qUEEDcemx6U8SyTbDp4U7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7fd1c557407923af3190282dba911a674e622308e464a4a6dbad5a19a3f537a","last_reissued_at":"2026-07-05T09:48:41.766813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:41.766813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jian Jiang, Jianyue Ge, Jianzhong Chen, Li Yu, Mengdi Liu, Qibo Chen, Shuchang Li, Weizhong Jin, Xuanjiang Guo, Yuchao Yan","submitted_at":"2024-12-13T02:36:29Z","abstract_excerpt":"Recent research on universal object detection aims to introduce language in a SoTA closed-set detector and then generalize the open-set concepts by constructing large-scale (text-region) datasets for training. However, these methods face two main challenges: (i) how to efficiently use the prior information in the prompts to genericise objects and (ii) how to reduce alignment bias in the downstream tasks, both leading to sub-optimal performance in some scenarios beyond pre-training. To address these challenges, we propose a strong universal detection foundation model called CP-DETR, which is co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09799","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/2412.09799/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":"2412.09799","created_at":"2026-07-05T09:48:41.766875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09799v1","created_at":"2026-07-05T09:48:41.766875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09799","created_at":"2026-07-05T09:48:41.766875+00:00"},{"alias_kind":"pith_short_12","alias_value":"476RYVLUA6JD","created_at":"2026-07-05T09:48:41.766875+00:00"},{"alias_kind":"pith_short_16","alias_value":"476RYVLUA6JDV4YZ","created_at":"2026-07-05T09:48:41.766875+00:00"},{"alias_kind":"pith_short_8","alias_value":"476RYVLU","created_at":"2026-07-05T09:48:41.766875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ","json":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ.json","graph_json":"https://pith.science/api/pith-number/476RYVLUA6JDV4YZAKBNXKIRUZ/graph.json","events_json":"https://pith.science/api/pith-number/476RYVLUA6JDV4YZAKBNXKIRUZ/events.json","paper":"https://pith.science/paper/476RYVLU"},"agent_actions":{"view_html":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ","download_json":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ.json","view_paper":"https://pith.science/paper/476RYVLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09799&json=true","fetch_graph":"https://pith.science/api/pith-number/476RYVLUA6JDV4YZAKBNXKIRUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/476RYVLUA6JDV4YZAKBNXKIRUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ/action/storage_attestation","attest_author":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ/action/author_attestation","sign_citation":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ/action/citation_signature","submit_replication":"https://pith.science/pith/476RYVLUA6JDV4YZAKBNXKIRUZ/action/replication_record"}},"created_at":"2026-07-05T09:48:41.766875+00:00","updated_at":"2026-07-05T09:48:41.766875+00:00"}