{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AHTG5PMGUODOGSRRSNPIHEMXPO","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":"a96dc3a25e02e860bb67b01b2de6c800c83a40451053020f7655a24722e77b7d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:25:51Z","title_canon_sha256":"ec3725c1fdb2e11ffcff38fa61896b681fe9ef3eed4275c3242f59d3008adc37"},"schema_version":"1.0","source":{"id":"2409.19961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19961","created_at":"2026-07-05T09:13:25Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19961v1","created_at":"2026-07-05T09:13:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19961","created_at":"2026-07-05T09:13:25Z"},{"alias_kind":"pith_short_12","alias_value":"AHTG5PMGUODO","created_at":"2026-07-05T09:13:25Z"},{"alias_kind":"pith_short_16","alias_value":"AHTG5PMGUODOGSRR","created_at":"2026-07-05T09:13:25Z"},{"alias_kind":"pith_short_8","alias_value":"AHTG5PMG","created_at":"2026-07-05T09:13:25Z"}],"graph_snapshots":[{"event_id":"sha256:edfd5cafb26b85360172fbdf55b2e8cf24be2fa04dc4f104112a3b89df1fe01b","target":"graph","created_at":"2026-07-05T09:13:25Z","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/2409.19961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine translation (MT) to create pseudo-parallel data pairs, establishing correspondence between visual and non-English textual data. However, aligning their representations poses challenges due to the significant semantic gap between vision and text, as well as the lower quality of non-English representations caused by pre-trained encoders and data noise. To overcome","authors_text":"Gang Hua, Hao Li, Le Wang, Qiang Zhou, Wei Tang, Yabing Wang, Zhibin Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:25:51Z","title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19961","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":"sha256:99231808a9d1a3885b0091ec9c46e2ac9cc6099d9816d455e2c6112b4b85cb05","target":"record","created_at":"2026-07-05T09:13:25Z","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":"a96dc3a25e02e860bb67b01b2de6c800c83a40451053020f7655a24722e77b7d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:25:51Z","title_canon_sha256":"ec3725c1fdb2e11ffcff38fa61896b681fe9ef3eed4275c3242f59d3008adc37"},"schema_version":"1.0","source":{"id":"2409.19961","kind":"arxiv","version":1}},"canonical_sha256":"01e66ebd86a386e34a31935e8391977b822cf742c603b09e3ea3aa46a929fa16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01e66ebd86a386e34a31935e8391977b822cf742c603b09e3ea3aa46a929fa16","first_computed_at":"2026-07-05T09:13:25.348280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:25.348280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AMtafWalIG8pozR5pV0Kz1vOqzoYiSxhAyteGc/NqkZIMMnSNAu0r+Evwhltv495C/cMy00GB0oXJCCNokr9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:25.348797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99231808a9d1a3885b0091ec9c46e2ac9cc6099d9816d455e2c6112b4b85cb05","sha256:edfd5cafb26b85360172fbdf55b2e8cf24be2fa04dc4f104112a3b89df1fe01b"],"state_sha256":"7e86fbfe3eb111f5c8fc36dc039d8db39541552c366a992601906bffcdc4a4f8"}