{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:757UIOYW7CMSF2GWTGE3ZY5OLG","short_pith_number":"pith:757UIOYW","schema_version":"1.0","canonical_sha256":"ff7f443b16f89922e8d69989bce3ae5984fe58a47e4b5c4240aba6ad5db45e3e","source":{"kind":"arxiv","id":"2502.08468","version":1},"attestation_state":"computed","paper":{"title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Furu Wei, Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Zhicheng Dou, Ziliang Zhao","submitted_at":"2025-02-12T15:03:33Z","abstract_excerpt":"Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space. However, the limited labeled multimodal data often hinders embedding performance. Recent approaches have leveraged data synthesis to address this problem, yet the quality of synthetic data remains a critical bottleneck. In this work, we identify three criteria for high-quality synthetic multimodal data. First, broad scope ensures that the generated data covers diverse tasks and modalities, making it applicable to va"},"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":"2502.08468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T15:03:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"77cdbc68f5a37ca3e0822cdfb9ef83f6d68ba318b1b8efa9c1859cb5f03fdfc9","abstract_canon_sha256":"e7d58f427211fa919ca038cb7a64ba6ec6fdfa0819da607f42c40b0c69b63379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:23.380202Z","signature_b64":"Iz/LJMwR4VjeENNN9fRHjuvpmwo1J91IMr+eC9w+uBNsnlyQZQWg0HyP8bIj0DGTFeGcKakDjD08EDXZzvvKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff7f443b16f89922e8d69989bce3ae5984fe58a47e4b5c4240aba6ad5db45e3e","last_reissued_at":"2026-07-05T10:13:23.379659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:23.379659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Furu Wei, Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Zhicheng Dou, Ziliang Zhao","submitted_at":"2025-02-12T15:03:33Z","abstract_excerpt":"Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space. However, the limited labeled multimodal data often hinders embedding performance. Recent approaches have leveraged data synthesis to address this problem, yet the quality of synthetic data remains a critical bottleneck. In this work, we identify three criteria for high-quality synthetic multimodal data. First, broad scope ensures that the generated data covers diverse tasks and modalities, making it applicable to va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08468","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/2502.08468/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":"2502.08468","created_at":"2026-07-05T10:13:23.379718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08468v1","created_at":"2026-07-05T10:13:23.379718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08468","created_at":"2026-07-05T10:13:23.379718+00:00"},{"alias_kind":"pith_short_12","alias_value":"757UIOYW7CMS","created_at":"2026-07-05T10:13:23.379718+00:00"},{"alias_kind":"pith_short_16","alias_value":"757UIOYW7CMSF2GW","created_at":"2026-07-05T10:13:23.379718+00:00"},{"alias_kind":"pith_short_8","alias_value":"757UIOYW","created_at":"2026-07-05T10:13:23.379718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.18095","citing_title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24621","citing_title":"FreeRet: MLLMs as Training-Free Retrievers","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG","json":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG.json","graph_json":"https://pith.science/api/pith-number/757UIOYW7CMSF2GWTGE3ZY5OLG/graph.json","events_json":"https://pith.science/api/pith-number/757UIOYW7CMSF2GWTGE3ZY5OLG/events.json","paper":"https://pith.science/paper/757UIOYW"},"agent_actions":{"view_html":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG","download_json":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG.json","view_paper":"https://pith.science/paper/757UIOYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08468&json=true","fetch_graph":"https://pith.science/api/pith-number/757UIOYW7CMSF2GWTGE3ZY5OLG/graph.json","fetch_events":"https://pith.science/api/pith-number/757UIOYW7CMSF2GWTGE3ZY5OLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG/action/storage_attestation","attest_author":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG/action/author_attestation","sign_citation":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG/action/citation_signature","submit_replication":"https://pith.science/pith/757UIOYW7CMSF2GWTGE3ZY5OLG/action/replication_record"}},"created_at":"2026-07-05T10:13:23.379718+00:00","updated_at":"2026-07-05T10:13:23.379718+00:00"}