{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5OGUP7U2G4YOFLKU44VJ7VHUPF","short_pith_number":"pith:5OGUP7U2","schema_version":"1.0","canonical_sha256":"eb8d47fe9a3730e2ad54e72a9fd4f479708fe09a857c7f14244fab55a85e7e9e","source":{"kind":"arxiv","id":"1707.04272","version":1},"attestation_state":"computed","paper":{"title":"Cultivating DNN Diversity for Large Scale Video Labelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eng-Jon Ong, Mikel Bober-Irizar, Miroslaw Bober, Sameed Husain","submitted_at":"2017-07-13T18:11:02Z","abstract_excerpt":"We investigate factors controlling DNN diversity in the context of the Google Cloud and YouTube-8M Video Understanding Challenge. While it is well-known that ensemble methods improve prediction performance, and that combining accurate but diverse predictors helps, there is little knowledge on how to best promote & measure DNN diversity. We show that diversity can be cultivated by some unexpected means, such as model over-fitting or dropout variations. We also present details of our solution to the video understanding problem, which ranked #7 in the Kaggle competition (competing as the Yeti tea"},"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":"1707.04272","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-13T18:11:02Z","cross_cats_sorted":[],"title_canon_sha256":"f278f582ecd6edeef3eb70931cb48bcf2b5c90d88c2f76a9f81a44db512ce7b2","abstract_canon_sha256":"80db291bb10e2731c96cb15a721de361dcc07ce084a40b409f4f7a1fb5f0e9b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:18.827139Z","signature_b64":"+x5SajnSX39dkkU6+T0p54nTz7vtlitS7A8KCCjodt0M8fjYoVTOxhOW1ruj8MLTkmpEfc4lhSPsZWM2lO8sBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb8d47fe9a3730e2ad54e72a9fd4f479708fe09a857c7f14244fab55a85e7e9e","last_reissued_at":"2026-05-18T00:40:18.826455Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:18.826455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cultivating DNN Diversity for Large Scale Video Labelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eng-Jon Ong, Mikel Bober-Irizar, Miroslaw Bober, Sameed Husain","submitted_at":"2017-07-13T18:11:02Z","abstract_excerpt":"We investigate factors controlling DNN diversity in the context of the Google Cloud and YouTube-8M Video Understanding Challenge. While it is well-known that ensemble methods improve prediction performance, and that combining accurate but diverse predictors helps, there is little knowledge on how to best promote & measure DNN diversity. We show that diversity can be cultivated by some unexpected means, such as model over-fitting or dropout variations. We also present details of our solution to the video understanding problem, which ranked #7 in the Kaggle competition (competing as the Yeti tea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04272","kind":"arxiv","version":1},"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":"1707.04272","created_at":"2026-05-18T00:40:18.826543+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.04272v1","created_at":"2026-05-18T00:40:18.826543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04272","created_at":"2026-05-18T00:40:18.826543+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OGUP7U2G4YO","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OGUP7U2G4YOFLKU","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OGUP7U2","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF","json":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF.json","graph_json":"https://pith.science/api/pith-number/5OGUP7U2G4YOFLKU44VJ7VHUPF/graph.json","events_json":"https://pith.science/api/pith-number/5OGUP7U2G4YOFLKU44VJ7VHUPF/events.json","paper":"https://pith.science/paper/5OGUP7U2"},"agent_actions":{"view_html":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF","download_json":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF.json","view_paper":"https://pith.science/paper/5OGUP7U2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.04272&json=true","fetch_graph":"https://pith.science/api/pith-number/5OGUP7U2G4YOFLKU44VJ7VHUPF/graph.json","fetch_events":"https://pith.science/api/pith-number/5OGUP7U2G4YOFLKU44VJ7VHUPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF/action/storage_attestation","attest_author":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF/action/author_attestation","sign_citation":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF/action/citation_signature","submit_replication":"https://pith.science/pith/5OGUP7U2G4YOFLKU44VJ7VHUPF/action/replication_record"}},"created_at":"2026-05-18T00:40:18.826543+00:00","updated_at":"2026-05-18T00:40:18.826543+00:00"}