{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PWUPYNX5G372REPQYNU72QTD7J","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":"67a8010213e89bdd7248e00a7644f5ee772124b0205cdf9e4b1866ee0fce9ae1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T02:49:55Z","title_canon_sha256":"b046f6de1d17714811a454541ae980a121839f1ee7a4204fbc76ac41235ee603"},"schema_version":"1.0","source":{"id":"2412.14475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14475","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14475v1","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14475","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"PWUPYNX5G372","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"PWUPYNX5G372REPQ","created_at":"2026-07-05T09:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"PWUPYNX5","created_at":"2026-07-05T09:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:b5758e546ab012f23756a1b2dc6003a8b78ba78369c3173a41e63a3fc02255df","target":"graph","created_at":"2026-07-05T09:51:47Z","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/2412.14475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the rapidly growing demand for multimodal retrieval, progress in this field remains severely constrained by a lack of training data. In this paper, we introduce MegaPairs, a novel data synthesis method that leverages vision language models (VLMs) and open-domain images, together with a massive synthetic dataset generated from this method. Our empirical analysis shows that MegaPairs generates high-quality data, enabling the multimodal retriever to significantly outperform the baseline model trained on 70$\\times$ more data from existing datasets. Moreover, since MegaPairs solely relies o","authors_text":"Bo Zhao, Chen Jason Zhang, Defu Lian, Junjie Zhou, Shitao Xiao, Yongping Xiong, Yueze Wang, Ze Liu, Zheng Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T02:49:55Z","title":"MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14475","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":"sha256:316880da8d2671620e2360b44edaeedb28b32717b5739def4d3e09ede9726491","target":"record","created_at":"2026-07-05T09:51:47Z","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":"67a8010213e89bdd7248e00a7644f5ee772124b0205cdf9e4b1866ee0fce9ae1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T02:49:55Z","title_canon_sha256":"b046f6de1d17714811a454541ae980a121839f1ee7a4204fbc76ac41235ee603"},"schema_version":"1.0","source":{"id":"2412.14475","kind":"arxiv","version":1}},"canonical_sha256":"7da8fc36fd36ffa891f0c369fd4263fa58ebebd7f518da3ef1f1951b830a31e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7da8fc36fd36ffa891f0c369fd4263fa58ebebd7f518da3ef1f1951b830a31e1","first_computed_at":"2026-07-05T09:51:47.881371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:47.881371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/5trIkIayYCwIxNHmqIWwytyWWTaLDjv6nsVUXWVszh10XG3TldUMnYcqU8kYoOJLIIVJvWzLMR+THn2RqrWDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:47.881875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:316880da8d2671620e2360b44edaeedb28b32717b5739def4d3e09ede9726491","sha256:b5758e546ab012f23756a1b2dc6003a8b78ba78369c3173a41e63a3fc02255df"],"state_sha256":"e15f104d49a1ca743c65fe3b94689188125650a87d908a7d54ce54966eaec15d"}