{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EUCKOERWMVH43WSPIP6VOL2PG6","short_pith_number":"pith:EUCKOERW","canonical_record":{"source":{"id":"1707.04555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-14T16:11:14Z","cross_cats_sorted":[],"title_canon_sha256":"3ceeb3dbbd79d6af02895dde949c1ec99e16012897624c9e5d9002e37c1146b6","abstract_canon_sha256":"2e60d355ecb9775bcfcc550d5c132658a0d27eee77ee2c4601d3f8f043034342"},"schema_version":"1.0"},"canonical_sha256":"2504a71236654fcdda4f43fd572f4f37a1b53bc0beb89e11d374dc1de00f5b5c","source":{"kind":"arxiv","id":"1707.04555","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.04555","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"1707.04555v1","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04555","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"EUCKOERWMVH4","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EUCKOERWMVH43WSP","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EUCKOERW","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EUCKOERWMVH43WSPIP6VOL2PG6","target":"record","payload":{"canonical_record":{"source":{"id":"1707.04555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-14T16:11:14Z","cross_cats_sorted":[],"title_canon_sha256":"3ceeb3dbbd79d6af02895dde949c1ec99e16012897624c9e5d9002e37c1146b6","abstract_canon_sha256":"2e60d355ecb9775bcfcc550d5c132658a0d27eee77ee2c4601d3f8f043034342"},"schema_version":"1.0"},"canonical_sha256":"2504a71236654fcdda4f43fd572f4f37a1b53bc0beb89e11d374dc1de00f5b5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:17.754476Z","signature_b64":"oOHWWvhOvMGPmm2ty3enGgDedw+IjgY1JZksGl4ZWd54qzh/0HT66Py+MHWaMShkr++rvzm7Bm/+WptOG8qwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2504a71236654fcdda4f43fd572f4f37a1b53bc0beb89e11d374dc1de00f5b5c","last_reissued_at":"2026-05-18T00:40:17.753665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:17.753665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.04555","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":"2026-05-18T00:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTRUuDKat6PeHsqN7N/6KsjtyhRCn+YIPU3X6eqOdk+5xvxUOeFuqPQgxpE3rZ/Uky21b7c74s7Eaa6TF208CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T20:25:42.918481Z"},"content_sha256":"7aaad2312e180af71401acf7ebf836845d1d8567432f9918b49ac3a5fa7f6082","schema_version":"1.0","event_id":"sha256:7aaad2312e180af71401acf7ebf836845d1d8567432f9918b49ac3a5fa7f6082"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EUCKOERWMVH43WSPIP6VOL2PG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Fu Li, Jie Zhou, Shilei Wen, Xiang Long, Xiao Liu, Yandong Li, Yunlong Bian, Zhichao Li","submitted_at":"2017-07-14T16:11:14Z","abstract_excerpt":"This paper describes our solution for the video recognition task of the Google Cloud and YouTube-8M Video Understanding Challenge that ranked the 3rd place. Because the challenge provides pre-extracted visual and audio features instead of the raw videos, we mainly investigate various temporal modeling approaches to aggregate the frame-level features for multi-label video recognition. Our system contains three major components: two-stream sequence model, fast-forward sequence model and temporal residual neural networks. Experiment results on the challenging Youtube-8M dataset demonstrate that o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04555","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":"2026-05-18T00:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nZ7l3Llx0NgXtFCLYZ5JIV85A8zGUtF1C6yIgB4usvEt6g9a8wriEtV6Ynb5AupEZ8h5CDzAbpHekWeOGHctBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T20:25:42.918941Z"},"content_sha256":"6c5d8d1a2fef5db8de96c68a27056058339ceeb361f0f7d8d59fdd23019f3f07","schema_version":"1.0","event_id":"sha256:6c5d8d1a2fef5db8de96c68a27056058339ceeb361f0f7d8d59fdd23019f3f07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/bundle.json","state_url":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EUCKOERWMVH43WSPIP6VOL2PG6/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":"2026-05-30T20:25:42Z","links":{"resolver":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6","bundle":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/bundle.json","state":"https://pith.science/pith/EUCKOERWMVH43WSPIP6VOL2PG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EUCKOERWMVH43WSPIP6VOL2PG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EUCKOERWMVH43WSPIP6VOL2PG6","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":"2e60d355ecb9775bcfcc550d5c132658a0d27eee77ee2c4601d3f8f043034342","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-14T16:11:14Z","title_canon_sha256":"3ceeb3dbbd79d6af02895dde949c1ec99e16012897624c9e5d9002e37c1146b6"},"schema_version":"1.0","source":{"id":"1707.04555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.04555","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"1707.04555v1","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04555","created_at":"2026-05-18T00:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"EUCKOERWMVH4","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EUCKOERWMVH43WSP","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EUCKOERW","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:6c5d8d1a2fef5db8de96c68a27056058339ceeb361f0f7d8d59fdd23019f3f07","target":"graph","created_at":"2026-05-18T00:40:17Z","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 paper describes our solution for the video recognition task of the Google Cloud and YouTube-8M Video Understanding Challenge that ranked the 3rd place. Because the challenge provides pre-extracted visual and audio features instead of the raw videos, we mainly investigate various temporal modeling approaches to aggregate the frame-level features for multi-label video recognition. Our system contains three major components: two-stream sequence model, fast-forward sequence model and temporal residual neural networks. Experiment results on the challenging Youtube-8M dataset demonstrate that o","authors_text":"Chuang Gan, Fu Li, Jie Zhou, Shilei Wen, Xiang Long, Xiao Liu, Yandong Li, Yunlong Bian, Zhichao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-14T16:11:14Z","title":"Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04555","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":"sha256:7aaad2312e180af71401acf7ebf836845d1d8567432f9918b49ac3a5fa7f6082","target":"record","created_at":"2026-05-18T00:40:17Z","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":"2e60d355ecb9775bcfcc550d5c132658a0d27eee77ee2c4601d3f8f043034342","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-14T16:11:14Z","title_canon_sha256":"3ceeb3dbbd79d6af02895dde949c1ec99e16012897624c9e5d9002e37c1146b6"},"schema_version":"1.0","source":{"id":"1707.04555","kind":"arxiv","version":1}},"canonical_sha256":"2504a71236654fcdda4f43fd572f4f37a1b53bc0beb89e11d374dc1de00f5b5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2504a71236654fcdda4f43fd572f4f37a1b53bc0beb89e11d374dc1de00f5b5c","first_computed_at":"2026-05-18T00:40:17.753665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:17.753665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oOHWWvhOvMGPmm2ty3enGgDedw+IjgY1JZksGl4ZWd54qzh/0HT66Py+MHWaMShkr++rvzm7Bm/+WptOG8qwDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:17.754476Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.04555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7aaad2312e180af71401acf7ebf836845d1d8567432f9918b49ac3a5fa7f6082","sha256:6c5d8d1a2fef5db8de96c68a27056058339ceeb361f0f7d8d59fdd23019f3f07"],"state_sha256":"7bf6622ad64a92c91d3a6d91f8a6c5a8a205cb7ca8e2f12a9c8bd2ffa833fe95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jj03x36wqO0pvUHYaV0Cwg+/lX022KLIPSH7CVedIEV+cz+PFTWGyDdVmLmdQQ8phqJESSkS66UZX+lQuBnNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T20:25:42.922215Z","bundle_sha256":"b387ccf1c0fe232b03374dcb18b48cc50e826f545c4d7711fbe51cc9b1c9db73"}}