{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z7N2CJFVRHYSIV2XKRB7JKEMPO","short_pith_number":"pith:Z7N2CJFV","schema_version":"1.0","canonical_sha256":"cfdba124b589f12457575443f4a88c7ba91fc4579f3987cf8999c72819960fe9","source":{"kind":"arxiv","id":"2009.05697","version":2},"attestation_state":"computed","paper":{"title":"YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Geng Yuan, Hongjia Li, Wei Niu, Xulong Tang, Yanyu Li, Yanzhi Wang, Yuxuan Cai","submitted_at":"2020-09-12T01:41:08Z","abstract_excerpt":"The rapid development and wide utilization of object detection techniques have aroused attention on both accuracy and speed of object detectors. However, the current state-of-the-art object detection works are either accuracy-oriented using a large model but leading to high latency or speed-oriented using a lightweight model but sacrificing accuracy. In this work, we propose YOLObile framework, a real-time object detection on mobile devices via compression-compilation co-design. A novel block-punched pruning scheme is proposed for any kernel size. To improve computational efficiency on mobile "},"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":"2009.05697","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-12T01:41:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e5267d8e78bab733da25b61e748a95ef374a81d38ed6be985d75faf47d4a8aea","abstract_canon_sha256":"63b7b4d45467d5d9471e5eedb5d584331d65425bc07fe5a6a9c32db631728953"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:55.673871Z","signature_b64":"vaxxqbwCkM7J+Cm2nDl4Bs0O9cBZzlwRJFUGBYX3c7aUK4Ul2IL5xgbWkzLdrRv6WTPBmYMz1MLl/L44z1Y/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfdba124b589f12457575443f4a88c7ba91fc4579f3987cf8999c72819960fe9","last_reissued_at":"2026-07-05T02:02:55.673338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:55.673338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Geng Yuan, Hongjia Li, Wei Niu, Xulong Tang, Yanyu Li, Yanzhi Wang, Yuxuan Cai","submitted_at":"2020-09-12T01:41:08Z","abstract_excerpt":"The rapid development and wide utilization of object detection techniques have aroused attention on both accuracy and speed of object detectors. However, the current state-of-the-art object detection works are either accuracy-oriented using a large model but leading to high latency or speed-oriented using a lightweight model but sacrificing accuracy. In this work, we propose YOLObile framework, a real-time object detection on mobile devices via compression-compilation co-design. A novel block-punched pruning scheme is proposed for any kernel size. To improve computational efficiency on mobile "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05697","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/2009.05697/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":"2009.05697","created_at":"2026-07-05T02:02:55.673416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.05697v2","created_at":"2026-07-05T02:02:55.673416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05697","created_at":"2026-07-05T02:02:55.673416+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7N2CJFVRHYS","created_at":"2026-07-05T02:02:55.673416+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7N2CJFVRHYSIV2X","created_at":"2026-07-05T02:02:55.673416+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7N2CJFV","created_at":"2026-07-05T02:02:55.673416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08339","citing_title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO","json":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO.json","graph_json":"https://pith.science/api/pith-number/Z7N2CJFVRHYSIV2XKRB7JKEMPO/graph.json","events_json":"https://pith.science/api/pith-number/Z7N2CJFVRHYSIV2XKRB7JKEMPO/events.json","paper":"https://pith.science/paper/Z7N2CJFV"},"agent_actions":{"view_html":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO","download_json":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO.json","view_paper":"https://pith.science/paper/Z7N2CJFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.05697&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7N2CJFVRHYSIV2XKRB7JKEMPO/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7N2CJFVRHYSIV2XKRB7JKEMPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO/action/storage_attestation","attest_author":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO/action/author_attestation","sign_citation":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO/action/citation_signature","submit_replication":"https://pith.science/pith/Z7N2CJFVRHYSIV2XKRB7JKEMPO/action/replication_record"}},"created_at":"2026-07-05T02:02:55.673416+00:00","updated_at":"2026-07-05T02:02:55.673416+00:00"}