{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DNT7PND36BBKQQ63Z6CD2WAG7A","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":"be6b8dce737581b9578f01890afca72c52faa62b850bf4a4e7a228ba4a1a9020","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-11T04:04:06Z","title_canon_sha256":"f2dc2394a25cabe6983d8e096d7c2d22f6239bea83deb6c1c78eec3286fe1f69"},"schema_version":"1.0","source":{"id":"1904.05521","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.05521","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"1904.05521v2","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05521","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"DNT7PND36BBK","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DNT7PND36BBKQQ63","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DNT7PND3","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:361266df92742282367c83e811a2ed35595b47831e80429a149b7dec4085f5f8","target":"graph","created_at":"2026-05-17T23:47:39Z","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":"We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts. The space unifies the concepts at different levels, including objects, attributes, relations, and full scenes. A contrastive learning approach is proposed for the fine-grained alignment from only image-caption pairs. Moreover, we present an effective approach for enforcing the coverage of semantic components that appear in the sentence. We demonstrate the robustness of Unified VSE in defending text-domain adversarial attacks on cross-modal retrieval tasks. Such robustness also empo","authors_text":"Hao Wu, Jiayuan Mao, Lei Li, Weiwei Sun, Wei-Ying Ma, Yufeng Zhang, Yuning Jiang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-11T04:04:06Z","title":"UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05521","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":"sha256:64ffd6122a2499f694f7a100009421dffb61b9210c95976ccde466b60098b92a","target":"record","created_at":"2026-05-17T23:47:39Z","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":"be6b8dce737581b9578f01890afca72c52faa62b850bf4a4e7a228ba4a1a9020","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-11T04:04:06Z","title_canon_sha256":"f2dc2394a25cabe6983d8e096d7c2d22f6239bea83deb6c1c78eec3286fe1f69"},"schema_version":"1.0","source":{"id":"1904.05521","kind":"arxiv","version":2}},"canonical_sha256":"1b67f7b47bf042a843dbcf843d5806f8166b4367af09a79ee70cd05e6fb4bb77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b67f7b47bf042a843dbcf843d5806f8166b4367af09a79ee70cd05e6fb4bb77","first_computed_at":"2026-05-17T23:47:39.221146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:39.221146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sed3EqatQoVXd4FDmxZoYXCa1HJh6/OQFm1KPfnZXOgLV5ALqjB+1JcmVE1Gtd4B4X8Q97neyElBYhq3L2ugCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:39.221568Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.05521","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64ffd6122a2499f694f7a100009421dffb61b9210c95976ccde466b60098b92a","sha256:361266df92742282367c83e811a2ed35595b47831e80429a149b7dec4085f5f8"],"state_sha256":"e796f110c4dd6d696b3548803bed5810390b1ff0bcbfe4242bd6515840bf9aff"}