{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:NTZHQTF4HPJNOH3DKX5SPVWFXB","short_pith_number":"pith:NTZHQTF4","canonical_record":{"source":{"id":"1612.00234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-01T13:11:29Z","cross_cats_sorted":[],"title_canon_sha256":"add00e9184f89a1b0a27720cb695f353a022e5a85c1e9c5858e0c8103ef6765a","abstract_canon_sha256":"598b942b15e963a367802d6c3ef7f0dfbfe2d073f290397eec52e656d8e598a5"},"schema_version":"1.0"},"canonical_sha256":"6cf2784cbc3bd2d71f6355fb27d6c5b8530be2f28ed4783861b41988218c3954","source":{"kind":"arxiv","id":"1612.00234","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00234","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00234v1","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00234","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"NTZHQTF4HPJN","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NTZHQTF4HPJNOH3D","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NTZHQTF4","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:NTZHQTF4HPJNOH3DKX5SPVWFXB","target":"record","payload":{"canonical_record":{"source":{"id":"1612.00234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-01T13:11:29Z","cross_cats_sorted":[],"title_canon_sha256":"add00e9184f89a1b0a27720cb695f353a022e5a85c1e9c5858e0c8103ef6765a","abstract_canon_sha256":"598b942b15e963a367802d6c3ef7f0dfbfe2d073f290397eec52e656d8e598a5"},"schema_version":"1.0"},"canonical_sha256":"6cf2784cbc3bd2d71f6355fb27d6c5b8530be2f28ed4783861b41988218c3954","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:05.666983Z","signature_b64":"kt/xxqY/adbDr5QNUvq+NTbvM5z6PyDNB1ZJeUDj6kTvm+UWjB0G64zoWQ0HKCuK5TIGd/pQRu2Y4R1pU+xVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cf2784cbc3bd2d71f6355fb27d6c5b8530be2f28ed4783861b41988218c3954","last_reissued_at":"2026-05-18T00:56:05.666282Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:05.666282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.00234","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":"2026-05-18T00:56:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dulmlkNEYM7BH9V+zf4Zt4smq22fY+/dpwbh2VuemPlVK/2ofAudZJCkjqQEOH5HqW/sX9jLxfAPcWjz9UOQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:52:25.246862Z"},"content_sha256":"6f5aed005af71aaf4c33d0de5ac12092be80546dedeff57ab5619c1197978c22","schema_version":"1.0","event_id":"sha256:6f5aed005af71aaf4c33d0de5ac12092be80546dedeff57ab5619c1197978c22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:NTZHQTF4HPJNOH3DKX5SPVWFXB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Captioning with Multi-Faceted Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Gerard de Melo, Xiang Long","submitted_at":"2016-12-01T13:11:29Z","abstract_excerpt":"Recently, video captioning has been attracting an increasing amount of interest, due to its potential for improving accessibility and information retrieval. While existing methods rely on different kinds of visual features and model structures, they do not fully exploit relevant semantic information. We present an extensible approach to jointly leverage several sorts of visual features and semantic attributes. Our novel architecture builds on LSTMs for sentence generation, with several attention layers and two multimodal layers. The attention mechanism learns to automatically select the most s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00234","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":"2026-05-18T00:56:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27nBihGM06df8oPanhwqDVy+9KVE4Fyl98FFtPNB5fFGacxvzohwTr5sUltVHImIj433ggQtsxvxaTHU8qqeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:52:25.247200Z"},"content_sha256":"853e8f003a2794f01f409acef09b15a5ddfeb7e5d9d1a7dcb91ab8eab14fa14d","schema_version":"1.0","event_id":"sha256:853e8f003a2794f01f409acef09b15a5ddfeb7e5d9d1a7dcb91ab8eab14fa14d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NTZHQTF4HPJNOH3DKX5SPVWFXB/bundle.json","state_url":"https://pith.science/pith/NTZHQTF4HPJNOH3DKX5SPVWFXB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NTZHQTF4HPJNOH3DKX5SPVWFXB/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":"2026-06-01T11:52:25Z","links":{"resolver":"https://pith.science/pith/NTZHQTF4HPJNOH3DKX5SPVWFXB","bundle":"https://pith.science/pith/NTZHQTF4HPJNOH3DKX5SPVWFXB/bundle.json","state":"https://pith.science/pith/NTZHQTF4HPJNOH3DKX5SPVWFXB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NTZHQTF4HPJNOH3DKX5SPVWFXB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:NTZHQTF4HPJNOH3DKX5SPVWFXB","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":"598b942b15e963a367802d6c3ef7f0dfbfe2d073f290397eec52e656d8e598a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-01T13:11:29Z","title_canon_sha256":"add00e9184f89a1b0a27720cb695f353a022e5a85c1e9c5858e0c8103ef6765a"},"schema_version":"1.0","source":{"id":"1612.00234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00234","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00234v1","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00234","created_at":"2026-05-18T00:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"NTZHQTF4HPJN","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NTZHQTF4HPJNOH3D","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NTZHQTF4","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:853e8f003a2794f01f409acef09b15a5ddfeb7e5d9d1a7dcb91ab8eab14fa14d","target":"graph","created_at":"2026-05-18T00:56:05Z","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":"Recently, video captioning has been attracting an increasing amount of interest, due to its potential for improving accessibility and information retrieval. While existing methods rely on different kinds of visual features and model structures, they do not fully exploit relevant semantic information. We present an extensible approach to jointly leverage several sorts of visual features and semantic attributes. Our novel architecture builds on LSTMs for sentence generation, with several attention layers and two multimodal layers. The attention mechanism learns to automatically select the most s","authors_text":"Chuang Gan, Gerard de Melo, Xiang Long","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-01T13:11:29Z","title":"Video Captioning with Multi-Faceted Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00234","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":"sha256:6f5aed005af71aaf4c33d0de5ac12092be80546dedeff57ab5619c1197978c22","target":"record","created_at":"2026-05-18T00:56:05Z","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":"598b942b15e963a367802d6c3ef7f0dfbfe2d073f290397eec52e656d8e598a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-01T13:11:29Z","title_canon_sha256":"add00e9184f89a1b0a27720cb695f353a022e5a85c1e9c5858e0c8103ef6765a"},"schema_version":"1.0","source":{"id":"1612.00234","kind":"arxiv","version":1}},"canonical_sha256":"6cf2784cbc3bd2d71f6355fb27d6c5b8530be2f28ed4783861b41988218c3954","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cf2784cbc3bd2d71f6355fb27d6c5b8530be2f28ed4783861b41988218c3954","first_computed_at":"2026-05-18T00:56:05.666282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:05.666282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kt/xxqY/adbDr5QNUvq+NTbvM5z6PyDNB1ZJeUDj6kTvm+UWjB0G64zoWQ0HKCuK5TIGd/pQRu2Y4R1pU+xVBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:05.666983Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.00234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f5aed005af71aaf4c33d0de5ac12092be80546dedeff57ab5619c1197978c22","sha256:853e8f003a2794f01f409acef09b15a5ddfeb7e5d9d1a7dcb91ab8eab14fa14d"],"state_sha256":"d88ac27b00bdc4ca5e0f8134e7392f0d25bdb9172ae6921a5424edfce3ea8a63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fJbz6N5z2fCloaPgMYktWiJ0CzPzTR++p1FH4wfQsUVQ5HwPBMlec9zfiefcwbBI2reOYdUVxZzc6GFAB/r3Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T11:52:25.249112Z","bundle_sha256":"0328a41fc06bf0b8d53f3a53a09523d6b509225f963fb2a6dab4585eed9a9af7"}}