{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:FAUCZYLLCD5HNUYCPMZRQRVOPK","short_pith_number":"pith:FAUCZYLL","canonical_record":{"source":{"id":"1505.01861","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T20:13:33Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"81f0926457903addfe9de543d76bba02fb9fc5f3b58614f4c41cf8f928fb928a","abstract_canon_sha256":"51cea961851a54493c4a7a9148c13a02686ebfd7e765dfbf315ff6d9388e3545"},"schema_version":"1.0"},"canonical_sha256":"28282ce16b10fa76d3027b331846ae7abaa5ac0598a2ea98d195d181ee2e5e1a","source":{"kind":"arxiv","id":"1505.01861","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.01861","created_at":"2026-05-18T01:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"1505.01861v3","created_at":"2026-05-18T01:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.01861","created_at":"2026-05-18T01:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"FAUCZYLLCD5H","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"FAUCZYLLCD5HNUYC","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"FAUCZYLL","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:FAUCZYLLCD5HNUYCPMZRQRVOPK","target":"record","payload":{"canonical_record":{"source":{"id":"1505.01861","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T20:13:33Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"81f0926457903addfe9de543d76bba02fb9fc5f3b58614f4c41cf8f928fb928a","abstract_canon_sha256":"51cea961851a54493c4a7a9148c13a02686ebfd7e765dfbf315ff6d9388e3545"},"schema_version":"1.0"},"canonical_sha256":"28282ce16b10fa76d3027b331846ae7abaa5ac0598a2ea98d195d181ee2e5e1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:57:41.583765Z","signature_b64":"AA4MTi5/Afh0lcewcfaeNVOKEO/+zFTTph2RO1bdA9kuMdaExUuiUH2KdZKYDxtkRyogCWWccwLKkdXXC4X9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28282ce16b10fa76d3027b331846ae7abaa5ac0598a2ea98d195d181ee2e5e1a","last_reissued_at":"2026-05-18T01:57:41.583120Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:57:41.583120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.01861","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:57:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMV8cPMaWX80xha6LIgVmBorTEOEosqMOnibmpoQHPLslIb+neLksp/4hX619GTs9ZLIGtOEQ6MHJ3SpZ5wpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:14:34.377868Z"},"content_sha256":"55e7f98d22a0871343d465c642ef9ac0071feb2b9777ab0c06f10ab2dc846e38","schema_version":"1.0","event_id":"sha256:55e7f98d22a0871343d465c642ef9ac0071feb2b9777ab0c06f10ab2dc846e38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:FAUCZYLLCD5HNUYCPMZRQRVOPK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jointly Modeling Embedding and Translation to Bridge Video and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Houqiang Li, Tao Mei, Ting Yao, Yingwei Pan, Yong Rui","submitted_at":"2015-05-07T20:13:33Z","abstract_excerpt":"Automatically describing video content with natural language is a fundamental challenge of multimedia. Recurrent Neural Networks (RNN), which models sequence dynamics, has attracted increasing attention on visual interpretation. However, most existing approaches generate a word locally with given previous words and the visual content, while the relationship between sentence semantics and visual content is not holistically exploited. As a result, the generated sentences may be contextually correct but the semantics (e.g., subjects, verbs or objects) are not true.\n  This paper presents a novel u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.01861","kind":"arxiv","version":3},"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":"2026-05-18T01:57:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bcLamJjLidrzfx5Cl+1d1Wuq0yQetj0WJr0nkx6+a+rICMYN+Ib6E6EDd/FSJIjOLZbVbzReWFBEwZ6NR4K7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:14:34.378242Z"},"content_sha256":"aec0f8851a437decfefb4165f26e36d6b08503048f6dc849c2fadd5fc2c09c5a","schema_version":"1.0","event_id":"sha256:aec0f8851a437decfefb4165f26e36d6b08503048f6dc849c2fadd5fc2c09c5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAUCZYLLCD5HNUYCPMZRQRVOPK/bundle.json","state_url":"https://pith.science/pith/FAUCZYLLCD5HNUYCPMZRQRVOPK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAUCZYLLCD5HNUYCPMZRQRVOPK/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":"2026-05-26T07:14:34Z","links":{"resolver":"https://pith.science/pith/FAUCZYLLCD5HNUYCPMZRQRVOPK","bundle":"https://pith.science/pith/FAUCZYLLCD5HNUYCPMZRQRVOPK/bundle.json","state":"https://pith.science/pith/FAUCZYLLCD5HNUYCPMZRQRVOPK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAUCZYLLCD5HNUYCPMZRQRVOPK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:FAUCZYLLCD5HNUYCPMZRQRVOPK","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":"51cea961851a54493c4a7a9148c13a02686ebfd7e765dfbf315ff6d9388e3545","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T20:13:33Z","title_canon_sha256":"81f0926457903addfe9de543d76bba02fb9fc5f3b58614f4c41cf8f928fb928a"},"schema_version":"1.0","source":{"id":"1505.01861","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.01861","created_at":"2026-05-18T01:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"1505.01861v3","created_at":"2026-05-18T01:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.01861","created_at":"2026-05-18T01:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"FAUCZYLLCD5H","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"FAUCZYLLCD5HNUYC","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"FAUCZYLL","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:aec0f8851a437decfefb4165f26e36d6b08503048f6dc849c2fadd5fc2c09c5a","target":"graph","created_at":"2026-05-18T01:57:41Z","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":"Automatically describing video content with natural language is a fundamental challenge of multimedia. Recurrent Neural Networks (RNN), which models sequence dynamics, has attracted increasing attention on visual interpretation. However, most existing approaches generate a word locally with given previous words and the visual content, while the relationship between sentence semantics and visual content is not holistically exploited. As a result, the generated sentences may be contextually correct but the semantics (e.g., subjects, verbs or objects) are not true.\n  This paper presents a novel u","authors_text":"Houqiang Li, Tao Mei, Ting Yao, Yingwei Pan, Yong Rui","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T20:13:33Z","title":"Jointly Modeling Embedding and Translation to Bridge Video and Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.01861","kind":"arxiv","version":3},"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":"sha256:55e7f98d22a0871343d465c642ef9ac0071feb2b9777ab0c06f10ab2dc846e38","target":"record","created_at":"2026-05-18T01:57:41Z","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":"51cea961851a54493c4a7a9148c13a02686ebfd7e765dfbf315ff6d9388e3545","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-07T20:13:33Z","title_canon_sha256":"81f0926457903addfe9de543d76bba02fb9fc5f3b58614f4c41cf8f928fb928a"},"schema_version":"1.0","source":{"id":"1505.01861","kind":"arxiv","version":3}},"canonical_sha256":"28282ce16b10fa76d3027b331846ae7abaa5ac0598a2ea98d195d181ee2e5e1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28282ce16b10fa76d3027b331846ae7abaa5ac0598a2ea98d195d181ee2e5e1a","first_computed_at":"2026-05-18T01:57:41.583120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:57:41.583120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AA4MTi5/Afh0lcewcfaeNVOKEO/+zFTTph2RO1bdA9kuMdaExUuiUH2KdZKYDxtkRyogCWWccwLKkdXXC4X9DA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:57:41.583765Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.01861","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55e7f98d22a0871343d465c642ef9ac0071feb2b9777ab0c06f10ab2dc846e38","sha256:aec0f8851a437decfefb4165f26e36d6b08503048f6dc849c2fadd5fc2c09c5a"],"state_sha256":"74eecb9e8dda43e98130ee5bd205a9e73a17ec845877265e0454b3dad6eb6959"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yHTV9WKVoXUO2yWluMy5Fd1pbpeGxFdlaNjYLMCGRKPxLa+O0bVQuQ8T9YOZ2NjtDqDtgFvqeRFMT+VkXBCxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:14:34.380985Z","bundle_sha256":"95f5a1cda624a7042f41512a4908acdae409eaf43fe7d3b36120de60e9af695a"}}