{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZTGSTZZDP7RA5KNNCU4LQ5HGZC","short_pith_number":"pith:ZTGSTZZD","schema_version":"1.0","canonical_sha256":"cccd29e7237fe20ea9ad1538b874e6c8bd04448a368349bf509a5a0770b5a990","source":{"kind":"arxiv","id":"1702.00824","version":5},"attestation_state":"computed","paper":{"title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Esteban Real, Jonathon Shlens, Stefano Mazzocchi, Vincent Vanhoucke, Xin Pan","submitted_at":"2017-02-02T20:58:02Z","abstract_excerpt":"We introduce a new large-scale data set of video URLs with densely-sampled object bounding box annotations called YouTube-BoundingBoxes (YT-BB). The data set consists of approximately 380,000 video segments about 19s long, automatically selected to feature objects in natural settings without editing or post-processing, with a recording quality often akin to that of a hand-held cell phone camera. The objects represent a subset of the MS COCO label set. All video segments were human-annotated with high-precision classification labels and bounding boxes at 1 frame per second. The use of a cascade"},"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":"1702.00824","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-02T20:58:02Z","cross_cats_sorted":[],"title_canon_sha256":"4c23b358570619e011e24f4a6bd4fc21a03353172d4aef56afadb82cac7f122c","abstract_canon_sha256":"ad2a08ff5a22c257786d250b70303d39793d3f4978417bc34424aaab98735969"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:56.489280Z","signature_b64":"pC4fDn+Ug7JTnoFbq/n8iNfY/SBYsedC4jaZQneDhl/PqkyCXsRAGKORjar1NjMhX8qxXN0/Voz1PXxd7EiSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cccd29e7237fe20ea9ad1538b874e6c8bd04448a368349bf509a5a0770b5a990","last_reissued_at":"2026-05-18T00:47:56.488586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:56.488586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Esteban Real, Jonathon Shlens, Stefano Mazzocchi, Vincent Vanhoucke, Xin Pan","submitted_at":"2017-02-02T20:58:02Z","abstract_excerpt":"We introduce a new large-scale data set of video URLs with densely-sampled object bounding box annotations called YouTube-BoundingBoxes (YT-BB). The data set consists of approximately 380,000 video segments about 19s long, automatically selected to feature objects in natural settings without editing or post-processing, with a recording quality often akin to that of a hand-held cell phone camera. The objects represent a subset of the MS COCO label set. All video segments were human-annotated with high-precision classification labels and bounding boxes at 1 frame per second. The use of a cascade"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00824","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1702.00824","created_at":"2026-05-18T00:47:56.488682+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.00824v5","created_at":"2026-05-18T00:47:56.488682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00824","created_at":"2026-05-18T00:47:56.488682+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTGSTZZDP7RA","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTGSTZZDP7RA5KNN","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTGSTZZD","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23045","citing_title":"The TIME Machine: On The Power of Motion for Efficient Perception","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC","json":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC.json","graph_json":"https://pith.science/api/pith-number/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/graph.json","events_json":"https://pith.science/api/pith-number/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/events.json","paper":"https://pith.science/paper/ZTGSTZZD"},"agent_actions":{"view_html":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC","download_json":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC.json","view_paper":"https://pith.science/paper/ZTGSTZZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.00824&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/action/storage_attestation","attest_author":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/action/author_attestation","sign_citation":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/action/citation_signature","submit_replication":"https://pith.science/pith/ZTGSTZZDP7RA5KNNCU4LQ5HGZC/action/replication_record"}},"created_at":"2026-05-18T00:47:56.488682+00:00","updated_at":"2026-05-18T00:47:56.488682+00:00"}