{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:P5DZL345XYEUT4CMPDYVL66N25","short_pith_number":"pith:P5DZL345","canonical_record":{"source":{"id":"1906.04375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-11T03:35:25Z","cross_cats_sorted":[],"title_canon_sha256":"a5cf910d145d98679ead7c97e5215e1f79764ebc0c7fd9d76cced9a718d4d5dc","abstract_canon_sha256":"93d31a2fb32a520557fea10979c7d80bf3c7b1061516df1c71f8187e806306d5"},"schema_version":"1.0"},"canonical_sha256":"7f4795ef9dbe0949f04c78f155fbcdd7635fd7ef47e615f57e7c4d02263c797f","source":{"kind":"arxiv","id":"1906.04375","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04375","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04375v1","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04375","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"pith_short_12","alias_value":"P5DZL345XYEU","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"P5DZL345XYEUT4CM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"P5DZL345","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:P5DZL345XYEUT4CMPDYVL66N25","target":"record","payload":{"canonical_record":{"source":{"id":"1906.04375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-11T03:35:25Z","cross_cats_sorted":[],"title_canon_sha256":"a5cf910d145d98679ead7c97e5215e1f79764ebc0c7fd9d76cced9a718d4d5dc","abstract_canon_sha256":"93d31a2fb32a520557fea10979c7d80bf3c7b1061516df1c71f8187e806306d5"},"schema_version":"1.0"},"canonical_sha256":"7f4795ef9dbe0949f04c78f155fbcdd7635fd7ef47e615f57e7c4d02263c797f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:39.497719Z","signature_b64":"nQRlZ1PjfEIQ+Mg9d4qi0ExfLcw5VLn8873hkpZxbmphITLkPFYXU7KGUP3ds2xI6kMd3CDsWJ3CzOsmAAy5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f4795ef9dbe0949f04c78f155fbcdd7635fd7ef47e615f57e7c4d02263c797f","last_reissued_at":"2026-05-17T23:43:39.496861Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:39.496861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.04375","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":"2026-05-17T23:43:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jvxzx7YWFbAXDsVZ1zV5T9tk2SGuZKBVwclWNcbwh+2vtQExYosm9pBvT9ivoTm33/G6tVs3Qo5HtJ+cgdUwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:08:27.913622Z"},"content_sha256":"d51813b13b8b4a79971026d8a3eee6bbd3598a09b46546fbc8bc970d65a77107","schema_version":"1.0","event_id":"sha256:d51813b13b8b4a79971026d8a3eee6bbd3598a09b46546fbc8bc970d65a77107"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:P5DZL345XYEUT4CMPDYVL66N25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junchao Zhang, Yuxin Peng","submitted_at":"2019-06-11T03:35:25Z","abstract_excerpt":"Video captioning aims to automatically generate natural language descriptions of video content, which has drawn a lot of attention recent years. Generating accurate and fine-grained captions needs to not only understand the global content of video, but also capture the detailed object information. Meanwhile, video representations have great impact on the quality of generated captions. Thus, it is important for video captioning to capture salient objects with their detailed temporal dynamics, and represent them using discriminative spatio-temporal representations. In this paper, we propose a ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04375","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":"2026-05-17T23:43:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BFtyedPSzSmnVUlCE2QoAotTifNM89V0D667Hy0Jb0v0gfHjFnK2X9TY0kkoBX9+fIdQsfHYuE5s+8OsBdtFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:08:27.914249Z"},"content_sha256":"6556fccde92374645d05f20aec6f72c7c56db35c2c12a8dc497df5a5cbba8bf7","schema_version":"1.0","event_id":"sha256:6556fccde92374645d05f20aec6f72c7c56db35c2c12a8dc497df5a5cbba8bf7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P5DZL345XYEUT4CMPDYVL66N25/bundle.json","state_url":"https://pith.science/pith/P5DZL345XYEUT4CMPDYVL66N25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P5DZL345XYEUT4CMPDYVL66N25/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":"2026-05-31T05:08:27Z","links":{"resolver":"https://pith.science/pith/P5DZL345XYEUT4CMPDYVL66N25","bundle":"https://pith.science/pith/P5DZL345XYEUT4CMPDYVL66N25/bundle.json","state":"https://pith.science/pith/P5DZL345XYEUT4CMPDYVL66N25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P5DZL345XYEUT4CMPDYVL66N25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:P5DZL345XYEUT4CMPDYVL66N25","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":"93d31a2fb32a520557fea10979c7d80bf3c7b1061516df1c71f8187e806306d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-11T03:35:25Z","title_canon_sha256":"a5cf910d145d98679ead7c97e5215e1f79764ebc0c7fd9d76cced9a718d4d5dc"},"schema_version":"1.0","source":{"id":"1906.04375","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04375","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04375v1","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04375","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"pith_short_12","alias_value":"P5DZL345XYEU","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"P5DZL345XYEUT4CM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"P5DZL345","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:6556fccde92374645d05f20aec6f72c7c56db35c2c12a8dc497df5a5cbba8bf7","target":"graph","created_at":"2026-05-17T23:43:39Z","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":"Video captioning aims to automatically generate natural language descriptions of video content, which has drawn a lot of attention recent years. Generating accurate and fine-grained captions needs to not only understand the global content of video, but also capture the detailed object information. Meanwhile, video representations have great impact on the quality of generated captions. Thus, it is important for video captioning to capture salient objects with their detailed temporal dynamics, and represent them using discriminative spatio-temporal representations. In this paper, we propose a ne","authors_text":"Junchao Zhang, Yuxin Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-11T03:35:25Z","title":"Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04375","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:d51813b13b8b4a79971026d8a3eee6bbd3598a09b46546fbc8bc970d65a77107","target":"record","created_at":"2026-05-17T23:43:39Z","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":"93d31a2fb32a520557fea10979c7d80bf3c7b1061516df1c71f8187e806306d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-11T03:35:25Z","title_canon_sha256":"a5cf910d145d98679ead7c97e5215e1f79764ebc0c7fd9d76cced9a718d4d5dc"},"schema_version":"1.0","source":{"id":"1906.04375","kind":"arxiv","version":1}},"canonical_sha256":"7f4795ef9dbe0949f04c78f155fbcdd7635fd7ef47e615f57e7c4d02263c797f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f4795ef9dbe0949f04c78f155fbcdd7635fd7ef47e615f57e7c4d02263c797f","first_computed_at":"2026-05-17T23:43:39.496861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:39.496861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nQRlZ1PjfEIQ+Mg9d4qi0ExfLcw5VLn8873hkpZxbmphITLkPFYXU7KGUP3ds2xI6kMd3CDsWJ3CzOsmAAy5Bg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:39.497719Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04375","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d51813b13b8b4a79971026d8a3eee6bbd3598a09b46546fbc8bc970d65a77107","sha256:6556fccde92374645d05f20aec6f72c7c56db35c2c12a8dc497df5a5cbba8bf7"],"state_sha256":"2c06eaedda6587dac9828beeb57f7d71b2a528da46ec7881e0c8671c98e23be5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KbjeBWZef/6rhU+KF6eG0EkKlRKSzfVDFg66iKSmv4FGhkzTXoZPAaN4NE31vO1tEWbrredgknmxklIEg1AxDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T05:08:27.917436Z","bundle_sha256":"16a46337286e5a790dafaab6c1146f5c7a110c49d35a093cac2d1094ab7457d5"}}