{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SBVIU3MHMOJSZ7HJLB5M353RRX","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":"0283582a8b370a744ea9102d372c3471730366b5992f6e624607c6ee0287a048","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T01:07:36Z","title_canon_sha256":"6c4497bd261fd8a46fdc8996f7974b901c1a26b3116208ea7438ea2a7cf04b56"},"schema_version":"1.0","source":{"id":"2403.06355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06355","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06355v1","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06355","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_12","alias_value":"SBVIU3MHMOJS","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_16","alias_value":"SBVIU3MHMOJSZ7HJ","created_at":"2026-07-05T07:54:22Z"},{"alias_kind":"pith_short_8","alias_value":"SBVIU3MH","created_at":"2026-07-05T07:54:22Z"}],"graph_snapshots":[{"event_id":"sha256:a02d8893ea9cef2c4ab7ba1d762095a8c2e3cf303e8c04a743b9f467316e9117","target":"graph","created_at":"2026-07-05T07:54:22Z","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/2403.06355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal semantic understanding requires integrating information from different modalities to extract users' real intention behind words. Most previous work applies a dual-encoder structure to separately encode image and text, but fails to learn cross-modal feature alignment, making it hard to achieve cross-modal deep information interaction. This paper proposes a novel CLIP-guided contrastive-learning-based architecture to perform multi-modal feature alignment, which projects the features derived from different modalities into a unified deep space. On multi-modal sarcasm detection (MMSD) a","authors_text":"Ke Chang, Ming Zhang, Yunfang Wu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T01:07:36Z","title":"Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06355","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":"sha256:3d9deba5e2a12f5e93f400b9d1d7a5b8eec5be64d429f5d3761b8189474d1684","target":"record","created_at":"2026-07-05T07:54:22Z","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":"0283582a8b370a744ea9102d372c3471730366b5992f6e624607c6ee0287a048","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T01:07:36Z","title_canon_sha256":"6c4497bd261fd8a46fdc8996f7974b901c1a26b3116208ea7438ea2a7cf04b56"},"schema_version":"1.0","source":{"id":"2403.06355","kind":"arxiv","version":1}},"canonical_sha256":"906a8a6d8763932cfce9587acdf7718de63613b345101753b519b46967cebcbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"906a8a6d8763932cfce9587acdf7718de63613b345101753b519b46967cebcbb","first_computed_at":"2026-07-05T07:54:22.400856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:22.400856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/JR8m55bT5ZiuyhcuugnjPE4m36Tb7VFGs7sQgj13JwIKJ0ApaERhU8N1BFbcZRqGnArngRnIiXVfvRgARC1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:22.401352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d9deba5e2a12f5e93f400b9d1d7a5b8eec5be64d429f5d3761b8189474d1684","sha256:a02d8893ea9cef2c4ab7ba1d762095a8c2e3cf303e8c04a743b9f467316e9117"],"state_sha256":"b2420e0b67add79674b6e589e18d6901aae2f1f182901e00e928ed5911a05ca3"}