{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AHTG5PMGUODOGSRRSNPIHEMXPO","short_pith_number":"pith:AHTG5PMG","schema_version":"1.0","canonical_sha256":"01e66ebd86a386e34a31935e8391977b822cf742c603b09e3ea3aa46a929fa16","source":{"kind":"arxiv","id":"2409.19961","version":1},"attestation_state":"computed","paper":{"title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gang Hua, Hao Li, Le Wang, Qiang Zhou, Wei Tang, Yabing Wang, Zhibin Wang","submitted_at":"2024-09-30T05:25:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.19961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T05:25:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ec3725c1fdb2e11ffcff38fa61896b681fe9ef3eed4275c3242f59d3008adc37","abstract_canon_sha256":"a96dc3a25e02e860bb67b01b2de6c800c83a40451053020f7655a24722e77b7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:25.348797Z","signature_b64":"AMtafWalIG8pozR5pV0Kz1vOqzoYiSxhAyteGc/NqkZIMMnSNAu0r+Evwhltv495C/cMy00GB0oXJCCNokr9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e66ebd86a386e34a31935e8391977b822cf742c603b09e3ea3aa46a929fa16","last_reissued_at":"2026-07-05T09:13:25.348280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:25.348280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gang Hua, Hao Li, Le Wang, Qiang Zhou, Wei Tang, Yabing Wang, Zhibin Wang","submitted_at":"2024-09-30T05:25:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19961","kind":"arxiv","version":1},"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/2409.19961/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.19961","created_at":"2026-07-05T09:13:25.348338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19961v1","created_at":"2026-07-05T09:13:25.348338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19961","created_at":"2026-07-05T09:13:25.348338+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHTG5PMGUODO","created_at":"2026-07-05T09:13:25.348338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHTG5PMGUODOGSRR","created_at":"2026-07-05T09:13:25.348338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHTG5PMG","created_at":"2026-07-05T09:13:25.348338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO","json":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO.json","graph_json":"https://pith.science/api/pith-number/AHTG5PMGUODOGSRRSNPIHEMXPO/graph.json","events_json":"https://pith.science/api/pith-number/AHTG5PMGUODOGSRRSNPIHEMXPO/events.json","paper":"https://pith.science/paper/AHTG5PMG"},"agent_actions":{"view_html":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO","download_json":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO.json","view_paper":"https://pith.science/paper/AHTG5PMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19961&json=true","fetch_graph":"https://pith.science/api/pith-number/AHTG5PMGUODOGSRRSNPIHEMXPO/graph.json","fetch_events":"https://pith.science/api/pith-number/AHTG5PMGUODOGSRRSNPIHEMXPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO/action/storage_attestation","attest_author":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO/action/author_attestation","sign_citation":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO/action/citation_signature","submit_replication":"https://pith.science/pith/AHTG5PMGUODOGSRRSNPIHEMXPO/action/replication_record"}},"created_at":"2026-07-05T09:13:25.348338+00:00","updated_at":"2026-07-05T09:13:25.348338+00:00"}