{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UFCUGBEVQR2IQLNRAPC7WF2JYU","short_pith_number":"pith:UFCUGBEV","canonical_record":{"source":{"id":"1908.04107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:12:17Z","cross_cats_sorted":[],"title_canon_sha256":"8d94bc4e2c48fb8cf024c01a5fe6258c27679b8bd9063c764852b5f78e57bb03","abstract_canon_sha256":"b073ded74e376d9a97d45ee47cefedd297ce0ae0143cca5d6e913e275769d93b"},"schema_version":"1.0"},"canonical_sha256":"a1454304958474882db103c5fb1749c501eb67d671c2b93bdf137b27255b1e70","source":{"kind":"arxiv","id":"1908.04107","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04107","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04107v2","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04107","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"pith_short_12","alias_value":"UFCUGBEVQR2I","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"pith_short_16","alias_value":"UFCUGBEVQR2IQLNR","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"pith_short_8","alias_value":"UFCUGBEV","created_at":"2026-07-04T23:58:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UFCUGBEVQR2IQLNRAPC7WF2JYU","target":"record","payload":{"canonical_record":{"source":{"id":"1908.04107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:12:17Z","cross_cats_sorted":[],"title_canon_sha256":"8d94bc4e2c48fb8cf024c01a5fe6258c27679b8bd9063c764852b5f78e57bb03","abstract_canon_sha256":"b073ded74e376d9a97d45ee47cefedd297ce0ae0143cca5d6e913e275769d93b"},"schema_version":"1.0"},"canonical_sha256":"a1454304958474882db103c5fb1749c501eb67d671c2b93bdf137b27255b1e70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:10.776098Z","signature_b64":"V7DTETHnmrvlchsbFwoJGvK7u+6m8FjoNAO/+BxuHQfta1K+yCdq8I6gzWAE7egeDD50aLW3RcNKm2jS2XPTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1454304958474882db103c5fb1749c501eb67d671c2b93bdf137b27255b1e70","last_reissued_at":"2026-07-04T23:58:10.775669Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:10.775669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.04107","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:58:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B0sRTp6MU/doXgtVTHTmG+3lVOBel8LEJJOkDmdMioZjakrsm6s+3M8Vzat9XKRHGTg6llLaktAG0os9/xbaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:31:26.860048Z"},"content_sha256":"524f9de4cdd7212320471f119c7a2d5c15244217b661ab496750d730e5adceb9","schema_version":"1.0","event_id":"sha256:524f9de4cdd7212320471f119c7a2d5c15244217b661ab496750d730e5adceb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UFCUGBEVQR2IQLNRAPC7WF2JYU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Unified Attention Networks for Vision-and-Language Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jun Yu, Qi Tian, Yuhao Cui, Zhou Yu","submitted_at":"2019-08-12T12:12:17Z","abstract_excerpt":"Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use co-attention models to associate each visual object (e.g., image region) with each textual object (e.g., query word). Despite the success of these co-attention models, they only model inter-modal interactions while neglecting intra-modal interactions. Here we propose a general `unified attention' model that simultaneously captures the intra- and inter-modal interaction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04107","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.04107/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-04T23:58:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afmEQ5RgdY7TpO3yVHDb2NAOWgA/admtXpCp19oe8GxdzbWwW1OF5gD0GaJbn6dbZItFvlrXyYM9wCFLArPMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:31:26.860573Z"},"content_sha256":"5585600683d96788de5e8db6141bff83e48db220b22808a3fb2104c0fd9e3aba","schema_version":"1.0","event_id":"sha256:5585600683d96788de5e8db6141bff83e48db220b22808a3fb2104c0fd9e3aba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/bundle.json","state_url":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/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":"2026-08-16T01:31:26Z","links":{"resolver":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU","bundle":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/bundle.json","state":"https://pith.science/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFCUGBEVQR2IQLNRAPC7WF2JYU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UFCUGBEVQR2IQLNRAPC7WF2JYU","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":"b073ded74e376d9a97d45ee47cefedd297ce0ae0143cca5d6e913e275769d93b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:12:17Z","title_canon_sha256":"8d94bc4e2c48fb8cf024c01a5fe6258c27679b8bd9063c764852b5f78e57bb03"},"schema_version":"1.0","source":{"id":"1908.04107","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04107","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04107v2","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04107","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"pith_short_12","alias_value":"UFCUGBEVQR2I","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"pith_short_16","alias_value":"UFCUGBEVQR2IQLNR","created_at":"2026-07-04T23:58:10Z"},{"alias_kind":"pith_short_8","alias_value":"UFCUGBEV","created_at":"2026-07-04T23:58:10Z"}],"graph_snapshots":[{"event_id":"sha256:5585600683d96788de5e8db6141bff83e48db220b22808a3fb2104c0fd9e3aba","target":"graph","created_at":"2026-07-04T23:58:10Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.04107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use co-attention models to associate each visual object (e.g., image region) with each textual object (e.g., query word). Despite the success of these co-attention models, they only model inter-modal interactions while neglecting intra-modal interactions. Here we propose a general `unified attention' model that simultaneously captures the intra- and inter-modal interaction","authors_text":"Dacheng Tao, Jun Yu, Qi Tian, Yuhao Cui, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:12:17Z","title":"Multimodal Unified Attention Networks for Vision-and-Language Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04107","kind":"arxiv","version":2},"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":"sha256:524f9de4cdd7212320471f119c7a2d5c15244217b661ab496750d730e5adceb9","target":"record","created_at":"2026-07-04T23:58:10Z","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":"b073ded74e376d9a97d45ee47cefedd297ce0ae0143cca5d6e913e275769d93b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:12:17Z","title_canon_sha256":"8d94bc4e2c48fb8cf024c01a5fe6258c27679b8bd9063c764852b5f78e57bb03"},"schema_version":"1.0","source":{"id":"1908.04107","kind":"arxiv","version":2}},"canonical_sha256":"a1454304958474882db103c5fb1749c501eb67d671c2b93bdf137b27255b1e70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1454304958474882db103c5fb1749c501eb67d671c2b93bdf137b27255b1e70","first_computed_at":"2026-07-04T23:58:10.775669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:58:10.775669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V7DTETHnmrvlchsbFwoJGvK7u+6m8FjoNAO/+BxuHQfta1K+yCdq8I6gzWAE7egeDD50aLW3RcNKm2jS2XPTBg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:58:10.776098Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04107","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:524f9de4cdd7212320471f119c7a2d5c15244217b661ab496750d730e5adceb9","sha256:5585600683d96788de5e8db6141bff83e48db220b22808a3fb2104c0fd9e3aba"],"state_sha256":"f3644e28c2007cf18fe79438a7e6d093bad7d59439389f2d7403745c92d207f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3wssMrRiszJJZEeZH8B3+bdPS0OfJxz84vP/0rb7Zve9dk2512Y6CFpYUMchhXyWyrBIfOXd6X7nDZjOZDxlDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:31:26.864480Z","bundle_sha256":"c3ef7e681fc17da8cefd0b92dc8706dc08d608dc68b49c69b4998de2d8777b00"}}