{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:757UIOYW7CMSF2GWTGE3ZY5OLG","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":"e7d58f427211fa919ca038cb7a64ba6ec6fdfa0819da607f42c40b0c69b63379","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T15:03:33Z","title_canon_sha256":"77cdbc68f5a37ca3e0822cdfb9ef83f6d68ba318b1b8efa9c1859cb5f03fdfc9"},"schema_version":"1.0","source":{"id":"2502.08468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08468","created_at":"2026-07-05T10:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08468v1","created_at":"2026-07-05T10:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08468","created_at":"2026-07-05T10:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"757UIOYW7CMS","created_at":"2026-07-05T10:13:23Z"},{"alias_kind":"pith_short_16","alias_value":"757UIOYW7CMSF2GW","created_at":"2026-07-05T10:13:23Z"},{"alias_kind":"pith_short_8","alias_value":"757UIOYW","created_at":"2026-07-05T10:13:23Z"}],"graph_snapshots":[{"event_id":"sha256:2b9818faa04667ad4a25b3921c462b10a5ec36e0934fb505745dd2b9724d2d0b","target":"graph","created_at":"2026-07-05T10:13:23Z","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/2502.08468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Furu Wei, Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Zhicheng Dou, Ziliang Zhao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T15:03:33Z","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08468","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":"sha256:89113be11774db7b19f9eacf099665983c22df80b5530780c3f38180af9463ab","target":"record","created_at":"2026-07-05T10:13:23Z","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":"e7d58f427211fa919ca038cb7a64ba6ec6fdfa0819da607f42c40b0c69b63379","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T15:03:33Z","title_canon_sha256":"77cdbc68f5a37ca3e0822cdfb9ef83f6d68ba318b1b8efa9c1859cb5f03fdfc9"},"schema_version":"1.0","source":{"id":"2502.08468","kind":"arxiv","version":1}},"canonical_sha256":"ff7f443b16f89922e8d69989bce3ae5984fe58a47e4b5c4240aba6ad5db45e3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff7f443b16f89922e8d69989bce3ae5984fe58a47e4b5c4240aba6ad5db45e3e","first_computed_at":"2026-07-05T10:13:23.379659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:23.379659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iz/LJMwR4VjeENNN9fRHjuvpmwo1J91IMr+eC9w+uBNsnlyQZQWg0HyP8bIj0DGTFeGcKakDjD08EDXZzvvKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:23.380202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89113be11774db7b19f9eacf099665983c22df80b5530780c3f38180af9463ab","sha256:2b9818faa04667ad4a25b3921c462b10a5ec36e0934fb505745dd2b9724d2d0b"],"state_sha256":"c8e368c1a4e91c7374bc4a5e7d5fa39fe865cb2644e7b96d2842a55dda9a6936"}