{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CKG4VAYO6C4PBIV7NW7CKQ2HEI","short_pith_number":"pith:CKG4VAYO","canonical_record":{"source":{"id":"1905.02963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-08T08:51:12Z","cross_cats_sorted":[],"title_canon_sha256":"5f7271a61cf69867f0e2465c4bcdb0bbefa4691bbb35e1d918cbd0f012168cb4","abstract_canon_sha256":"5303b6056ddf46bdd940918552990b17533521e87d535e19a151c9a93d9cd335"},"schema_version":"1.0"},"canonical_sha256":"128dca830ef0b8f0a2bf6dbe25434722253fbc2449c6536da52b22d7ff71f021","source":{"kind":"arxiv","id":"1905.02963","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.02963","created_at":"2026-05-17T23:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"1905.02963v1","created_at":"2026-05-17T23:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02963","created_at":"2026-05-17T23:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"CKG4VAYO6C4P","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CKG4VAYO6C4PBIV7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CKG4VAYO","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CKG4VAYO6C4PBIV7NW7CKQ2HEI","target":"record","payload":{"canonical_record":{"source":{"id":"1905.02963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-08T08:51:12Z","cross_cats_sorted":[],"title_canon_sha256":"5f7271a61cf69867f0e2465c4bcdb0bbefa4691bbb35e1d918cbd0f012168cb4","abstract_canon_sha256":"5303b6056ddf46bdd940918552990b17533521e87d535e19a151c9a93d9cd335"},"schema_version":"1.0"},"canonical_sha256":"128dca830ef0b8f0a2bf6dbe25434722253fbc2449c6536da52b22d7ff71f021","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:43.265134Z","signature_b64":"C6NOV5A+q2znNtf4AsXS/Eg6I6rtgZ0GFUz8ojDyTiC3i8Wzyx0k7axh27FXdEzNChFZ4CrVbi2es2vmDHztCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"128dca830ef0b8f0a2bf6dbe25434722253fbc2449c6536da52b22d7ff71f021","last_reissued_at":"2026-05-17T23:46:43.264689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:43.264689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.02963","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":"2026-05-17T23:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QK2tfFw77oNMiv0J8Gbs9oW1j3JmFZFrqhDR9kstMd/pNE7j85vEZyQGUsdXcMuNV51OoMOeOO+g+tU4CJGOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:40:46.919118Z"},"content_sha256":"23d7b07768ad0781431e15a9e54eb43a87a41cd5a3127b0ecfe28dc4dc5e67a7","schema_version":"1.0","event_id":"sha256:23d7b07768ad0781431e15a9e54eb43a87a41cd5a3127b0ecfe28dc4dc5e67a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CKG4VAYO6C4PBIV7NW7CKQ2HEI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Semantic Attention Network for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chunfeng Yuan, Liang Sun, Weiming Hu, Zhengjun Zha","submitted_at":"2019-05-08T08:51:12Z","abstract_excerpt":"Inspired by the fact that different modalities in videos carry complementary information, we propose a Multimodal Semantic Attention Network(MSAN), which is a new encoder-decoder framework incorporating multimodal semantic attributes for video captioning. In the encoding phase, we detect and generate multimodal semantic attributes by formulating it as a multi-label classification problem. Moreover, we add auxiliary classification loss to our model that can obtain more effective visual features and high-level multimodal semantic attribute distributions for sufficient video encoding. In the deco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02963","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":"2026-05-17T23:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JFBt38XxP1R8bgETfGK1/nyKBHdRx0gGIn0CXObuxjkKDFO20hiM9coKsiLaPPVl5MRBt7VVANSPvKjFrkoqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:40:46.919798Z"},"content_sha256":"7a1553872f3c920bff3dc3c818b6dd1f75d17181f74c09dbaea88b701961f9eb","schema_version":"1.0","event_id":"sha256:7a1553872f3c920bff3dc3c818b6dd1f75d17181f74c09dbaea88b701961f9eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/bundle.json","state_url":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/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":"2026-05-28T18:40:46Z","links":{"resolver":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI","bundle":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/bundle.json","state":"https://pith.science/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKG4VAYO6C4PBIV7NW7CKQ2HEI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CKG4VAYO6C4PBIV7NW7CKQ2HEI","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":"5303b6056ddf46bdd940918552990b17533521e87d535e19a151c9a93d9cd335","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-08T08:51:12Z","title_canon_sha256":"5f7271a61cf69867f0e2465c4bcdb0bbefa4691bbb35e1d918cbd0f012168cb4"},"schema_version":"1.0","source":{"id":"1905.02963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.02963","created_at":"2026-05-17T23:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"1905.02963v1","created_at":"2026-05-17T23:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02963","created_at":"2026-05-17T23:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"CKG4VAYO6C4P","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CKG4VAYO6C4PBIV7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CKG4VAYO","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:7a1553872f3c920bff3dc3c818b6dd1f75d17181f74c09dbaea88b701961f9eb","target":"graph","created_at":"2026-05-17T23:46:43Z","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":"Inspired by the fact that different modalities in videos carry complementary information, we propose a Multimodal Semantic Attention Network(MSAN), which is a new encoder-decoder framework incorporating multimodal semantic attributes for video captioning. In the encoding phase, we detect and generate multimodal semantic attributes by formulating it as a multi-label classification problem. Moreover, we add auxiliary classification loss to our model that can obtain more effective visual features and high-level multimodal semantic attribute distributions for sufficient video encoding. In the deco","authors_text":"Bing Li, Chunfeng Yuan, Liang Sun, Weiming Hu, Zhengjun Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-08T08:51:12Z","title":"Multimodal Semantic Attention Network for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02963","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":"sha256:23d7b07768ad0781431e15a9e54eb43a87a41cd5a3127b0ecfe28dc4dc5e67a7","target":"record","created_at":"2026-05-17T23:46:43Z","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":"5303b6056ddf46bdd940918552990b17533521e87d535e19a151c9a93d9cd335","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-08T08:51:12Z","title_canon_sha256":"5f7271a61cf69867f0e2465c4bcdb0bbefa4691bbb35e1d918cbd0f012168cb4"},"schema_version":"1.0","source":{"id":"1905.02963","kind":"arxiv","version":1}},"canonical_sha256":"128dca830ef0b8f0a2bf6dbe25434722253fbc2449c6536da52b22d7ff71f021","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"128dca830ef0b8f0a2bf6dbe25434722253fbc2449c6536da52b22d7ff71f021","first_computed_at":"2026-05-17T23:46:43.264689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:43.264689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6NOV5A+q2znNtf4AsXS/Eg6I6rtgZ0GFUz8ojDyTiC3i8Wzyx0k7axh27FXdEzNChFZ4CrVbi2es2vmDHztCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:43.265134Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.02963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23d7b07768ad0781431e15a9e54eb43a87a41cd5a3127b0ecfe28dc4dc5e67a7","sha256:7a1553872f3c920bff3dc3c818b6dd1f75d17181f74c09dbaea88b701961f9eb"],"state_sha256":"f9df428f2388d60dba5194022620847582481d363becc666eea1110478744780"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ynUof76e/bsaYBCqAldiWVPxH6sA0bW/IzSEXd9GACGxF8aj+GZtqGDBVkd1mDjxYgJUOZh7tSgtzocJwq0YCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:40:46.922454Z","bundle_sha256":"32a40c57feb6e2b55c34f5454703a22728e3ed0ad28327dbd318b125e7a0444c"}}