{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3UUL4M2ZKVLD4REQDHYY5TXNSF","short_pith_number":"pith:3UUL4M2Z","schema_version":"1.0","canonical_sha256":"dd28be335955563e449019f18eceed91668c98cac3f589234d3484b879f278d6","source":{"kind":"arxiv","id":"1706.05150","version":1},"attestation_state":"computed","paper":{"title":"The Monkeytyping Solution to the YouTube-8M Video Understanding Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He-Da Wang, Ji Wu, Teng Zhang","submitted_at":"2017-06-16T05:39:53Z","abstract_excerpt":"This article describes the final solution of team monkeytyping, who finished in second place in the YouTube-8M video understanding challenge. The dataset used in this challenge is a large-scale benchmark for multi-label video classification. We extend the work in [1] and propose several improvements for frame sequence modeling. We propose a network structure called Chaining that can better capture the interactions between labels. Also, we report our approaches in dealing with multi-scale information and attention pooling. In addition, We find that using the output of model ensemble as a side t"},"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":"1706.05150","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-16T05:39:53Z","cross_cats_sorted":[],"title_canon_sha256":"3f9d7a032c283087f00442397a91b407384a419d622dfccd915ee8110348abf0","abstract_canon_sha256":"cfd3e3f56018dd516dd98af841490d4af8e1764ee5d2aa6abd7b58f40a002482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:14.584187Z","signature_b64":"BauxYBZj0eE+3vLL32etn+aLhkG2fofmScXQgsqI5xpDpntRRdulyi8mAI9ZlZAFAcmrSSeeYHlV25J9TeVnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd28be335955563e449019f18eceed91668c98cac3f589234d3484b879f278d6","last_reissued_at":"2026-05-18T00:42:14.583519Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:14.583519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Monkeytyping Solution to the YouTube-8M Video Understanding Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He-Da Wang, Ji Wu, Teng Zhang","submitted_at":"2017-06-16T05:39:53Z","abstract_excerpt":"This article describes the final solution of team monkeytyping, who finished in second place in the YouTube-8M video understanding challenge. The dataset used in this challenge is a large-scale benchmark for multi-label video classification. We extend the work in [1] and propose several improvements for frame sequence modeling. We propose a network structure called Chaining that can better capture the interactions between labels. Also, we report our approaches in dealing with multi-scale information and attention pooling. In addition, We find that using the output of model ensemble as a side t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.05150","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":"1706.05150","created_at":"2026-05-18T00:42:14.583639+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.05150v1","created_at":"2026-05-18T00:42:14.583639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05150","created_at":"2026-05-18T00:42:14.583639+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UUL4M2ZKVLD","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UUL4M2ZKVLD4REQ","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UUL4M2Z","created_at":"2026-05-18T12:30:58.224056+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/3UUL4M2ZKVLD4REQDHYY5TXNSF","json":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF.json","graph_json":"https://pith.science/api/pith-number/3UUL4M2ZKVLD4REQDHYY5TXNSF/graph.json","events_json":"https://pith.science/api/pith-number/3UUL4M2ZKVLD4REQDHYY5TXNSF/events.json","paper":"https://pith.science/paper/3UUL4M2Z"},"agent_actions":{"view_html":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF","download_json":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF.json","view_paper":"https://pith.science/paper/3UUL4M2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.05150&json=true","fetch_graph":"https://pith.science/api/pith-number/3UUL4M2ZKVLD4REQDHYY5TXNSF/graph.json","fetch_events":"https://pith.science/api/pith-number/3UUL4M2ZKVLD4REQDHYY5TXNSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/action/storage_attestation","attest_author":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/action/author_attestation","sign_citation":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/action/citation_signature","submit_replication":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/action/replication_record"}},"created_at":"2026-05-18T00:42:14.583639+00:00","updated_at":"2026-05-18T00:42:14.583639+00:00"}