{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J4C2PLE3CVHHLJSRRT4KUAL62T","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":"554c067009d2776305c7f48a8c5a66794ac093f5f37b9d9833943ce63fd80996","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T03:58:38Z","title_canon_sha256":"eee3f895e78ca228a1f1249fd6a5deb5f0666b5cb283102036d653c5945f0a11"},"schema_version":"1.0","source":{"id":"2502.12513","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12513","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12513v3","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12513","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_12","alias_value":"J4C2PLE3CVHH","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_16","alias_value":"J4C2PLE3CVHHLJSR","created_at":"2026-07-05T11:48:47Z"},{"alias_kind":"pith_short_8","alias_value":"J4C2PLE3","created_at":"2026-07-05T11:48:47Z"}],"graph_snapshots":[{"event_id":"sha256:94b349b4d408d868f41ff63756cc51a89cfcfbec2f608859d0440c0245b52505","target":"graph","created_at":"2026-07-05T11:48:47Z","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/2502.12513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaoyi Zhang, Dongnan Liu, Jiankang Deng, Kaicheng Yang, Tiancheng Gu, Weidong Cai, Xiang An, Yin Xie, Ziyong Feng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T03:58:38Z","title":"RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12513","kind":"arxiv","version":3},"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:df0f70cfc7d9d7596d1f40b7ad69a95273390b28d1eacd46eff4779a033245ea","target":"record","created_at":"2026-07-05T11:48:47Z","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":"554c067009d2776305c7f48a8c5a66794ac093f5f37b9d9833943ce63fd80996","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T03:58:38Z","title_canon_sha256":"eee3f895e78ca228a1f1249fd6a5deb5f0666b5cb283102036d653c5945f0a11"},"schema_version":"1.0","source":{"id":"2502.12513","kind":"arxiv","version":3}},"canonical_sha256":"4f05a7ac9b154e75a6518cf8aa017ed4da939c913dc27f943ead7225a6d449b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f05a7ac9b154e75a6518cf8aa017ed4da939c913dc27f943ead7225a6d449b2","first_computed_at":"2026-07-05T11:48:47.613803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:47.613803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/6ZY/D7x1IC+fS7Twaf1sM9u1neK0VSk/dsOtW10aXRNoIh9EefB73mZyGFC6o5Y+iji6QyP50djq4OCNKQOAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:47.614308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12513","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df0f70cfc7d9d7596d1f40b7ad69a95273390b28d1eacd46eff4779a033245ea","sha256:94b349b4d408d868f41ff63756cc51a89cfcfbec2f608859d0440c0245b52505"],"state_sha256":"6c1b809b5ba16834cdd099eeb05fc7d2a7409ff49ce120f461312f82e97cba46"}