{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G726HRPDDRTSMBNFPPZRXCNIND","short_pith_number":"pith:G726HRPD","schema_version":"1.0","canonical_sha256":"37f5e3c5e31c672605a57bf31b89a868c37b5caf6df605129c5b92677575ada3","source":{"kind":"arxiv","id":"2103.14027","version":3},"attestation_state":"computed","paper":{"title":"USB: Universal-Scale Object Detection Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yosuke Shinya","submitted_at":"2021-03-25T17:59:15Z","abstract_excerpt":"Benchmarks, such as COCO, play a crucial role in object detection. However, existing benchmarks are insufficient in scale variation, and their protocols are inadequate for fair comparison. In this paper, we introduce the Universal-Scale object detection Benchmark (USB). USB has variations in object scales and image domains by incorporating COCO with the recently proposed Waymo Open Dataset and Manga109-s dataset. To enable fair comparison and inclusive research, we propose training and evaluation protocols. They have multiple divisions for training epochs and evaluation image resolutions, like"},"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":"2103.14027","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-25T17:59:15Z","cross_cats_sorted":[],"title_canon_sha256":"003fe57f74a5bc9be5a6b7c776f0d912ca2bf80f71768398febb9cbfdbd6be63","abstract_canon_sha256":"793d8955347ea7deef8a8ef8b5e9b10d87640610d081facd2f4bbe521f5d8594"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:47.963209Z","signature_b64":"ofCGQUmMy1TyVu36CMEPbYJNwB04PVTLhAFIZtMbJjBPv0kdDv4YQDO3FwGaUjGj/y6pqMOD74+EcPH//wapCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37f5e3c5e31c672605a57bf31b89a868c37b5caf6df605129c5b92677575ada3","last_reissued_at":"2026-07-05T05:12:47.962812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:47.962812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"USB: Universal-Scale Object Detection Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yosuke Shinya","submitted_at":"2021-03-25T17:59:15Z","abstract_excerpt":"Benchmarks, such as COCO, play a crucial role in object detection. However, existing benchmarks are insufficient in scale variation, and their protocols are inadequate for fair comparison. In this paper, we introduce the Universal-Scale object detection Benchmark (USB). USB has variations in object scales and image domains by incorporating COCO with the recently proposed Waymo Open Dataset and Manga109-s dataset. To enable fair comparison and inclusive research, we propose training and evaluation protocols. They have multiple divisions for training epochs and evaluation image resolutions, like"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14027","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/2103.14027/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":"2103.14027","created_at":"2026-07-05T05:12:47.962866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14027v3","created_at":"2026-07-05T05:12:47.962866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14027","created_at":"2026-07-05T05:12:47.962866+00:00"},{"alias_kind":"pith_short_12","alias_value":"G726HRPDDRTS","created_at":"2026-07-05T05:12:47.962866+00:00"},{"alias_kind":"pith_short_16","alias_value":"G726HRPDDRTSMBNF","created_at":"2026-07-05T05:12:47.962866+00:00"},{"alias_kind":"pith_short_8","alias_value":"G726HRPD","created_at":"2026-07-05T05:12:47.962866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06332","citing_title":"Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detection","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND","json":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND.json","graph_json":"https://pith.science/api/pith-number/G726HRPDDRTSMBNFPPZRXCNIND/graph.json","events_json":"https://pith.science/api/pith-number/G726HRPDDRTSMBNFPPZRXCNIND/events.json","paper":"https://pith.science/paper/G726HRPD"},"agent_actions":{"view_html":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND","download_json":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND.json","view_paper":"https://pith.science/paper/G726HRPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14027&json=true","fetch_graph":"https://pith.science/api/pith-number/G726HRPDDRTSMBNFPPZRXCNIND/graph.json","fetch_events":"https://pith.science/api/pith-number/G726HRPDDRTSMBNFPPZRXCNIND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND/action/storage_attestation","attest_author":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND/action/author_attestation","sign_citation":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND/action/citation_signature","submit_replication":"https://pith.science/pith/G726HRPDDRTSMBNFPPZRXCNIND/action/replication_record"}},"created_at":"2026-07-05T05:12:47.962866+00:00","updated_at":"2026-07-05T05:12:47.962866+00:00"}