{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OMFBHIZUB3AX7T2P5LKUPICXP5","short_pith_number":"pith:OMFBHIZU","schema_version":"1.0","canonical_sha256":"730a13a3340ec17fcf4fead547a0577f6563ef8d2a61103ec8cd002cbe0637d0","source":{"kind":"arxiv","id":"2203.16250","version":3},"attestation_state":"computed","paper":{"title":"PP-YOLOE: An evolved version of YOLO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baohua Lai, Cheng Cui, Guanzhong Wang, Kaipeng Deng, Qingqing Dang, Qinyao Chang, Shangliang Xu, Shengyu Wei, Wenyu Lv, Xinxin Wang, Yuning Du","submitted_at":"2022-03-30T12:31:39Z","abstract_excerpt":"In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL. We provide s/m/l/x models for different practice scenarios. As a result, PP-YOLOE-l achieves 51.4 mAP on COCO test-dev and 78.1 FPS on Tesla V100, yielding a remarkable improvement of (+1.9 AP, +13.35% speed up) and (+1.3 AP, +24.96% speed up), compared to the previous state"},"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":"2203.16250","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-30T12:31:39Z","cross_cats_sorted":[],"title_canon_sha256":"d4d069022c06df65703c31772f150f57df5a7f9856dd8790172c1addd4e8cf65","abstract_canon_sha256":"50fe113b9584af97bb3bfbab9cb55f2cb738c20a2cd7561484938386734ad98b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:10.993950Z","signature_b64":"wRYQzgXycW/vtTXPWNp5+uRXzZuOpK6ztTHsQj6ceVfvIcjp9i3CgfOGhnZ5Pzu34BuUNmH8i5sM8STA4ZtSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"730a13a3340ec17fcf4fead547a0577f6563ef8d2a61103ec8cd002cbe0637d0","last_reissued_at":"2026-07-05T05:24:10.993524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:10.993524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PP-YOLOE: An evolved version of YOLO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baohua Lai, Cheng Cui, Guanzhong Wang, Kaipeng Deng, Qingqing Dang, Qinyao Chang, Shangliang Xu, Shengyu Wei, Wenyu Lv, Xinxin Wang, Yuning Du","submitted_at":"2022-03-30T12:31:39Z","abstract_excerpt":"In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL. We provide s/m/l/x models for different practice scenarios. As a result, PP-YOLOE-l achieves 51.4 mAP on COCO test-dev and 78.1 FPS on Tesla V100, yielding a remarkable improvement of (+1.9 AP, +13.35% speed up) and (+1.3 AP, +24.96% speed up), compared to the previous state"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16250","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/2203.16250/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":"2203.16250","created_at":"2026-07-05T05:24:10.993584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16250v3","created_at":"2026-07-05T05:24:10.993584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16250","created_at":"2026-07-05T05:24:10.993584+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMFBHIZUB3AX","created_at":"2026-07-05T05:24:10.993584+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMFBHIZUB3AX7T2P","created_at":"2026-07-05T05:24:10.993584+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMFBHIZU","created_at":"2026-07-05T05:24:10.993584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03508","citing_title":"Structure-Guided Mixed Masked Pretraining and Spatial Continuity Regularization for Printed Circuit Board Defect Detection","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30151","citing_title":"AERIS: Aerial-Edge Role-Driven Intelligence at Runtime via Orchestrated Language-Model Swarm","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30215","citing_title":"Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07965","citing_title":"Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03349","citing_title":"YOLOv11 Demystified: A Practical Guide to High-Performance Object Detection","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19233","citing_title":"Adaptive Slicing-Assisted Hyper Inference for Enhanced Small Object Detection in High-Resolution Imagery","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5","json":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5.json","graph_json":"https://pith.science/api/pith-number/OMFBHIZUB3AX7T2P5LKUPICXP5/graph.json","events_json":"https://pith.science/api/pith-number/OMFBHIZUB3AX7T2P5LKUPICXP5/events.json","paper":"https://pith.science/paper/OMFBHIZU"},"agent_actions":{"view_html":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5","download_json":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5.json","view_paper":"https://pith.science/paper/OMFBHIZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16250&json=true","fetch_graph":"https://pith.science/api/pith-number/OMFBHIZUB3AX7T2P5LKUPICXP5/graph.json","fetch_events":"https://pith.science/api/pith-number/OMFBHIZUB3AX7T2P5LKUPICXP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5/action/storage_attestation","attest_author":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5/action/author_attestation","sign_citation":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5/action/citation_signature","submit_replication":"https://pith.science/pith/OMFBHIZUB3AX7T2P5LKUPICXP5/action/replication_record"}},"created_at":"2026-07-05T05:24:10.993584+00:00","updated_at":"2026-07-05T05:24:10.993584+00:00"}