{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3UUL4M2ZKVLD4REQDHYY5TXNSF","short_pith_number":"pith:3UUL4M2Z","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"},"canonical_sha256":"dd28be335955563e449019f18eceed91668c98cac3f589234d3484b879f278d6","source":{"kind":"arxiv","id":"1706.05150","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.05150","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1706.05150v1","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05150","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"3UUL4M2ZKVLD","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3UUL4M2ZKVLD4REQ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3UUL4M2Z","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3UUL4M2ZKVLD4REQDHYY5TXNSF","target":"record","payload":{"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"},"canonical_sha256":"dd28be335955563e449019f18eceed91668c98cac3f589234d3484b879f278d6","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"},"source_kind":"arxiv","source_id":"1706.05150","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vg32+Pr9IAp9+ZKyfAxRqCNEHg5o9xXH+oaKhPIQYgN6LHzQ+dwi7qhIX/IicSw6vxHz4ruAWFjgTvPmL6gJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:08:06.991416Z"},"content_sha256":"baa24ffb25591092c6ea63b8565552b8de983cfc91ffe5f9e5f6a422998e5938","schema_version":"1.0","event_id":"sha256:baa24ffb25591092c6ea63b8565552b8de983cfc91ffe5f9e5f6a422998e5938"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3UUL4M2ZKVLD4REQDHYY5TXNSF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VPGvPTEJ30sh0C2GxwPY5d5gpCdNOvIjvhsGZEYWAWnT/pljBeV+nelpwp/RMmHvC3bqqoG1wX82INAqi3mLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:08:06.992055Z"},"content_sha256":"f3334bdbbe282715de2be02bca270504e0ff2bf8f0e19883c604cfa419f8fb2f","schema_version":"1.0","event_id":"sha256:f3334bdbbe282715de2be02bca270504e0ff2bf8f0e19883c604cfa419f8fb2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/bundle.json","state_url":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T14:08:06Z","links":{"resolver":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF","bundle":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/bundle.json","state":"https://pith.science/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3UUL4M2ZKVLD4REQDHYY5TXNSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3UUL4M2ZKVLD4REQDHYY5TXNSF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cfd3e3f56018dd516dd98af841490d4af8e1764ee5d2aa6abd7b58f40a002482","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-16T05:39:53Z","title_canon_sha256":"3f9d7a032c283087f00442397a91b407384a419d622dfccd915ee8110348abf0"},"schema_version":"1.0","source":{"id":"1706.05150","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.05150","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1706.05150v1","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05150","created_at":"2026-05-18T00:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"3UUL4M2ZKVLD","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3UUL4M2ZKVLD4REQ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3UUL4M2Z","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:f3334bdbbe282715de2be02bca270504e0ff2bf8f0e19883c604cfa419f8fb2f","target":"graph","created_at":"2026-05-18T00:42:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"He-Da Wang, Ji Wu, Teng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-16T05:39:53Z","title":"The Monkeytyping Solution to the YouTube-8M Video Understanding Challenge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.05150","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:baa24ffb25591092c6ea63b8565552b8de983cfc91ffe5f9e5f6a422998e5938","target":"record","created_at":"2026-05-18T00:42:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cfd3e3f56018dd516dd98af841490d4af8e1764ee5d2aa6abd7b58f40a002482","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-16T05:39:53Z","title_canon_sha256":"3f9d7a032c283087f00442397a91b407384a419d622dfccd915ee8110348abf0"},"schema_version":"1.0","source":{"id":"1706.05150","kind":"arxiv","version":1}},"canonical_sha256":"dd28be335955563e449019f18eceed91668c98cac3f589234d3484b879f278d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd28be335955563e449019f18eceed91668c98cac3f589234d3484b879f278d6","first_computed_at":"2026-05-18T00:42:14.583519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:14.583519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BauxYBZj0eE+3vLL32etn+aLhkG2fofmScXQgsqI5xpDpntRRdulyi8mAI9ZlZAFAcmrSSeeYHlV25J9TeVnCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:14.584187Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.05150","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baa24ffb25591092c6ea63b8565552b8de983cfc91ffe5f9e5f6a422998e5938","sha256:f3334bdbbe282715de2be02bca270504e0ff2bf8f0e19883c604cfa419f8fb2f"],"state_sha256":"a824a4e5618de001a9209683ead325447c0b92bcae2db53de885bb9d0e9d99d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDrbfuIzhhUIphCT7JW8uISBMQ9rntNJXB/9dug58/ay2gqvaHoAvwTG4JUt3MmFN6xFKnyaWgInpKJAC7wCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:08:06.995798Z","bundle_sha256":"27b386fd96530f7bc28de68e28b0a2b2486cd98bb43207e1a562e701a236616d"}}