{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J4C2PLE3CVHHLJSRRT4KUAL62T","short_pith_number":"pith:J4C2PLE3","schema_version":"1.0","canonical_sha256":"4f05a7ac9b154e75a6518cf8aa017ed4da939c913dc27f943ead7225a6d449b2","source":{"kind":"arxiv","id":"2502.12513","version":3},"attestation_state":"computed","paper":{"title":"RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyi Zhang, Dongnan Liu, Jiankang Deng, Kaicheng Yang, Tiancheng Gu, Weidong Cai, Xiang An, Yin Xie, Ziyong Feng","submitted_at":"2025-02-18T03:58:38Z","abstract_excerpt":"After pre-training on extensive image-text pairs, Contrastive Language-Image Pre-training (CLIP) demonstrates promising performance on a wide variety of benchmarks. However, a substantial volume of multimodal interleaved documents remains underutilized for contrastive vision-language representation learning. To fully leverage these unpaired documents, we initially establish a Real-World Data Extraction pipeline to extract high-quality images and texts. Then we design a hierarchical retrieval method to efficiently associate each image with multiple semantically relevant realistic texts. To furt"},"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":"2502.12513","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T03:58:38Z","cross_cats_sorted":[],"title_canon_sha256":"eee3f895e78ca228a1f1249fd6a5deb5f0666b5cb283102036d653c5945f0a11","abstract_canon_sha256":"554c067009d2776305c7f48a8c5a66794ac093f5f37b9d9833943ce63fd80996"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:47.614308Z","signature_b64":"/6ZY/D7x1IC+fS7Twaf1sM9u1neK0VSk/dsOtW10aXRNoIh9EefB73mZyGFC6o5Y+iji6QyP50djq4OCNKQOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f05a7ac9b154e75a6518cf8aa017ed4da939c913dc27f943ead7225a6d449b2","last_reissued_at":"2026-07-05T11:48:47.613803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:47.613803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyi Zhang, Dongnan Liu, Jiankang Deng, Kaicheng Yang, Tiancheng Gu, Weidong Cai, Xiang An, Yin Xie, Ziyong Feng","submitted_at":"2025-02-18T03:58:38Z","abstract_excerpt":"After pre-training on extensive image-text pairs, Contrastive Language-Image Pre-training (CLIP) demonstrates promising performance on a wide variety of benchmarks. However, a substantial volume of multimodal interleaved documents remains underutilized for contrastive vision-language representation learning. To fully leverage these unpaired documents, we initially establish a Real-World Data Extraction pipeline to extract high-quality images and texts. Then we design a hierarchical retrieval method to efficiently associate each image with multiple semantically relevant realistic texts. To furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12513","kind":"arxiv","version":3},"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/2502.12513/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":"2502.12513","created_at":"2026-07-05T11:48:47.613865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12513v3","created_at":"2026-07-05T11:48:47.613865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12513","created_at":"2026-07-05T11:48:47.613865+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4C2PLE3CVHH","created_at":"2026-07-05T11:48:47.613865+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4C2PLE3CVHHLJSR","created_at":"2026-07-05T11:48:47.613865+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4C2PLE3","created_at":"2026-07-05T11:48:47.613865+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/J4C2PLE3CVHHLJSRRT4KUAL62T","json":"https://pith.science/pith/J4C2PLE3CVHHLJSRRT4KUAL62T.json","graph_json":"https://pith.science/api/pith-number/J4C2PLE3CVHHLJSRRT4KUAL62T/graph.json","events_json":"https://pith.science/api/pith-number/J4C2PLE3CVHHLJSRRT4KUAL62T/events.json","paper":"https://pith.science/paper/J4C2PLE3"},"agent_actions":{"view_html":"https://pith.science/pith/J4C2PLE3CVHHLJSRRT4KUAL62T","download_json":"https://pith.science/pith/J4C2PLE3CVHHLJSRRT4KUAL62T.json","view_paper":"https://pith.science/paper/J4C2PLE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12513&json=true","fetch_graph":"https://pith.science/api/pith-number/J4C2PLE3CVHHLJSRRT4KUAL62T/graph.json","fetch_events":"https://pith.science/api/pith-number/J4C2PLE3CVHHLJSRRT4KUAL62T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4C2PLE3CVHHLJSRRT4KUAL62T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4C2PLE3CVHHLJSRRT4KUAL62T/action/storage_attestation","attest_author":"https://pith.science/pith/J4C2PLE3CVHHLJSRRT4KUAL62T/action/author_attestation","sign_citation":"https://pith.science/pith/J4C2PLE3CVHHLJSRRT4KUAL62T/action/citation_signature","submit_replication":"https://pith.science/pith/J4C2PLE3CVHHLJSRRT4KUAL62T/action/replication_record"}},"created_at":"2026-07-05T11:48:47.613865+00:00","updated_at":"2026-07-05T11:48:47.613865+00:00"}