{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AZZU7XPNKWPMXSNSKDKN5UMQT3","short_pith_number":"pith:AZZU7XPN","canonical_record":{"source":{"id":"1704.01502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-05T16:06:09Z","cross_cats_sorted":[],"title_canon_sha256":"4f8c34ab0e1e4e5fdedcbf5162e3a5ff542e64f907ffa5943d7b673fc9550197","abstract_canon_sha256":"6895c464c90cf977c3fe679e64af27989f002c611c46a1537f4c58663d668d89"},"schema_version":"1.0"},"canonical_sha256":"06734fdded559ecbc9b250d4ded1909ee0cd1d8e06db36518451be685d9b8f90","source":{"kind":"arxiv","id":"1704.01502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01502","created_at":"2026-05-18T00:46:56Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01502v1","created_at":"2026-05-18T00:46:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01502","created_at":"2026-05-18T00:46:56Z"},{"alias_kind":"pith_short_12","alias_value":"AZZU7XPNKWPM","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AZZU7XPNKWPMXSNS","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AZZU7XPN","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AZZU7XPNKWPMXSNSKDKN5UMQT3","target":"record","payload":{"canonical_record":{"source":{"id":"1704.01502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-05T16:06:09Z","cross_cats_sorted":[],"title_canon_sha256":"4f8c34ab0e1e4e5fdedcbf5162e3a5ff542e64f907ffa5943d7b673fc9550197","abstract_canon_sha256":"6895c464c90cf977c3fe679e64af27989f002c611c46a1537f4c58663d668d89"},"schema_version":"1.0"},"canonical_sha256":"06734fdded559ecbc9b250d4ded1909ee0cd1d8e06db36518451be685d9b8f90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:56.288925Z","signature_b64":"XIBwTWh1KIMeq8i5tL4+LG4S1idBk2hYApVeVJgdLidAGGW8kx9MyCyVpihxAlqVzTtt1YINvAPZSlMsb7rYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06734fdded559ecbc9b250d4ded1909ee0cd1d8e06db36518451be685d9b8f90","last_reissued_at":"2026-05-18T00:46:56.288488Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:56.288488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.01502","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":"2026-05-18T00:46:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrZmtKNn90749fAhYEt0iVsiFHrmu+gJpygBEOQz6x5QUKyfmLRy7oHTRb3uCVOU8lFSGgi6Y4IOTeaCrnb9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:58:52.563887Z"},"content_sha256":"c3553bde71f9ac566d2926702d220011692f16543c79343dae2e0d5c4a869683","schema_version":"1.0","event_id":"sha256:c3553bde71f9ac566d2926702d220011692f16543c79343dae2e0d5c4a869683"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AZZU7XPNKWPMXSNSKDKN5UMQT3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly Supervised Dense Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianguo Li, Minjun Li, Xiangyang Xue, Yu-Gang Jiang, Yurong Chen, Zhiqiang Shen, Zhou Su","submitted_at":"2017-04-05T16:06:09Z","abstract_excerpt":"This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences. The proposed method is trained without explicit annotation of fine-grained sentence to video region-sequence correspondence, but is only based on weak video-level sentence annotations. It differs from existing video captioning systems in three technical aspects. First, we propose lexical fully convolutional neural networks (Lexical-FCN) with weakly supervised multi-instance multi-label learning to weakly li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01502","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":"2026-05-18T00:46:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHkYdRvX0b3LEmEQSzjMF6QhpfWojU/oLKambcnAc/0vY7CetmtGfhGYrg6V9j7BosMfbEBZFG0Jtc1cXUfGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:58:52.564536Z"},"content_sha256":"44e30e4a86e5cf7e63b6303f64f6d120a8570229ab22dd5db6104e5b4f148fca","schema_version":"1.0","event_id":"sha256:44e30e4a86e5cf7e63b6303f64f6d120a8570229ab22dd5db6104e5b4f148fca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZZU7XPNKWPMXSNSKDKN5UMQT3/bundle.json","state_url":"https://pith.science/pith/AZZU7XPNKWPMXSNSKDKN5UMQT3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZZU7XPNKWPMXSNSKDKN5UMQT3/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":"2026-06-12T02:58:52Z","links":{"resolver":"https://pith.science/pith/AZZU7XPNKWPMXSNSKDKN5UMQT3","bundle":"https://pith.science/pith/AZZU7XPNKWPMXSNSKDKN5UMQT3/bundle.json","state":"https://pith.science/pith/AZZU7XPNKWPMXSNSKDKN5UMQT3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZZU7XPNKWPMXSNSKDKN5UMQT3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AZZU7XPNKWPMXSNSKDKN5UMQT3","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":"6895c464c90cf977c3fe679e64af27989f002c611c46a1537f4c58663d668d89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-05T16:06:09Z","title_canon_sha256":"4f8c34ab0e1e4e5fdedcbf5162e3a5ff542e64f907ffa5943d7b673fc9550197"},"schema_version":"1.0","source":{"id":"1704.01502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01502","created_at":"2026-05-18T00:46:56Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01502v1","created_at":"2026-05-18T00:46:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01502","created_at":"2026-05-18T00:46:56Z"},{"alias_kind":"pith_short_12","alias_value":"AZZU7XPNKWPM","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"AZZU7XPNKWPMXSNS","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"AZZU7XPN","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:44e30e4a86e5cf7e63b6303f64f6d120a8570229ab22dd5db6104e5b4f148fca","target":"graph","created_at":"2026-05-18T00:46:56Z","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 focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences. The proposed method is trained without explicit annotation of fine-grained sentence to video region-sequence correspondence, but is only based on weak video-level sentence annotations. It differs from existing video captioning systems in three technical aspects. First, we propose lexical fully convolutional neural networks (Lexical-FCN) with weakly supervised multi-instance multi-label learning to weakly li","authors_text":"Jianguo Li, Minjun Li, Xiangyang Xue, Yu-Gang Jiang, Yurong Chen, Zhiqiang Shen, Zhou Su","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-05T16:06:09Z","title":"Weakly Supervised Dense Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01502","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:c3553bde71f9ac566d2926702d220011692f16543c79343dae2e0d5c4a869683","target":"record","created_at":"2026-05-18T00:46:56Z","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":"6895c464c90cf977c3fe679e64af27989f002c611c46a1537f4c58663d668d89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-05T16:06:09Z","title_canon_sha256":"4f8c34ab0e1e4e5fdedcbf5162e3a5ff542e64f907ffa5943d7b673fc9550197"},"schema_version":"1.0","source":{"id":"1704.01502","kind":"arxiv","version":1}},"canonical_sha256":"06734fdded559ecbc9b250d4ded1909ee0cd1d8e06db36518451be685d9b8f90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06734fdded559ecbc9b250d4ded1909ee0cd1d8e06db36518451be685d9b8f90","first_computed_at":"2026-05-18T00:46:56.288488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:56.288488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XIBwTWh1KIMeq8i5tL4+LG4S1idBk2hYApVeVJgdLidAGGW8kx9MyCyVpihxAlqVzTtt1YINvAPZSlMsb7rYCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:56.288925Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.01502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3553bde71f9ac566d2926702d220011692f16543c79343dae2e0d5c4a869683","sha256:44e30e4a86e5cf7e63b6303f64f6d120a8570229ab22dd5db6104e5b4f148fca"],"state_sha256":"f9dbf44cd86a2d552941ea02d73b1081807711a368fcab442922c63519c14c0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V3L58ldctWapneIVxS5oldkbs2HUBsyFs+5yM49rROzX9CaH18t6fUHiKGFs/Tpomm65tLrSNs3WapgyLmCpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T02:58:52.568515Z","bundle_sha256":"c4a0448e2fc8a3f45b876ea102ff9e7ca579b2102d063afe23a56aaaa7dd6262"}}