{"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"}