{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OMIV2WHS74W3LPMBLE25QWCDJV","short_pith_number":"pith:OMIV2WHS","schema_version":"1.0","canonical_sha256":"73115d58f2ff2db5bd815935d858434d4ce814ae7b3af3c05df0a08dfa5f53bb","source":{"kind":"arxiv","id":"2409.08475","version":3},"attestation_state":"computed","paper":{"title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunlong Xia, Feng Lv, Shuo Wang, Yifeng Shi","submitted_at":"2024-09-13T02:02:07Z","abstract_excerpt":"RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense supervision detectors like the YOLO series, the Hungarian matching provides much sparser supervision, leading to insufficient model training and difficult to achieve optimal results. To address these issues, we proposed a hierarchical dense positive supervision method based on RT-DETR, named RT-DETRv3. Firstly, we introduce a CNN-based auxiliary branch that provides dense supervision that collaborates with the origina"},"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":"2409.08475","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T02:02:07Z","cross_cats_sorted":[],"title_canon_sha256":"cf614bb403d13cd8f5b2eaf192c670d61a675327283a8d37d6ab51f291dd6585","abstract_canon_sha256":"edbc663255bbbb78dead0fe1b4c6c67e9f3384a8543f27446487f115420a5290"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:36.651955Z","signature_b64":"WPATY+P9ZHd8Jqtx8GEZHUT8spnGlaCfGocPNTmV9fk8Nh1srWRMdAkFd3ifvhsv1y3PRkfMPBecpYQDsWuwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73115d58f2ff2db5bd815935d858434d4ce814ae7b3af3c05df0a08dfa5f53bb","last_reissued_at":"2026-07-05T09:51:36.651399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:36.651399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunlong Xia, Feng Lv, Shuo Wang, Yifeng Shi","submitted_at":"2024-09-13T02:02:07Z","abstract_excerpt":"RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense supervision detectors like the YOLO series, the Hungarian matching provides much sparser supervision, leading to insufficient model training and difficult to achieve optimal results. To address these issues, we proposed a hierarchical dense positive supervision method based on RT-DETR, named RT-DETRv3. Firstly, we introduce a CNN-based auxiliary branch that provides dense supervision that collaborates with the origina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08475","kind":"arxiv","version":3},"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/2409.08475/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":"2409.08475","created_at":"2026-07-05T09:51:36.651459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08475v3","created_at":"2026-07-05T09:51:36.651459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08475","created_at":"2026-07-05T09:51:36.651459+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMIV2WHS74W3","created_at":"2026-07-05T09:51:36.651459+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMIV2WHS74W3LPMB","created_at":"2026-07-05T09:51:36.651459+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMIV2WHS","created_at":"2026-07-05T09:51:36.651459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08562","citing_title":"Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV","json":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV.json","graph_json":"https://pith.science/api/pith-number/OMIV2WHS74W3LPMBLE25QWCDJV/graph.json","events_json":"https://pith.science/api/pith-number/OMIV2WHS74W3LPMBLE25QWCDJV/events.json","paper":"https://pith.science/paper/OMIV2WHS"},"agent_actions":{"view_html":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV","download_json":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV.json","view_paper":"https://pith.science/paper/OMIV2WHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08475&json=true","fetch_graph":"https://pith.science/api/pith-number/OMIV2WHS74W3LPMBLE25QWCDJV/graph.json","fetch_events":"https://pith.science/api/pith-number/OMIV2WHS74W3LPMBLE25QWCDJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV/action/storage_attestation","attest_author":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV/action/author_attestation","sign_citation":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV/action/citation_signature","submit_replication":"https://pith.science/pith/OMIV2WHS74W3LPMBLE25QWCDJV/action/replication_record"}},"created_at":"2026-07-05T09:51:36.651459+00:00","updated_at":"2026-07-05T09:51:36.651459+00:00"}