{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ROMSPYG2TII6G7I2QMLGJY7EZZ","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":"62b7a1b49c381c3c12e21bcc8512a2d6a31cdb49b3932770b095511f9a172da8","cross_cats_sorted":["cs.CV","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T22:28:12Z","title_canon_sha256":"0bba5ea07adbd5e530fea0116c7ebb1c3bd33b4351d3b71659410af626456e7d"},"schema_version":"1.0","source":{"id":"2412.08802","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08802","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08802v2","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08802","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_12","alias_value":"ROMSPYG2TII6","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_16","alias_value":"ROMSPYG2TII6G7I2","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_8","alias_value":"ROMSPYG2","created_at":"2026-07-05T10:53:39Z"}],"graph_snapshots":[{"event_id":"sha256:fedc014113d90f7b706df3a33d854c6035d07142c664a3b540e21ace07c48b30","target":"graph","created_at":"2026-07-05T10:53:39Z","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/2412.08802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) has been widely used for crossmodal information retrieval and multimodal understanding tasks. However, CLIP models are mainly optimized for crossmodal vision-language tasks and underperform in single-mode text tasks. Moreover, these models are often trained on English datasets and therefore lack multilingual understanding. Additionally, from a visual understanding perspective, previous CLIP-based models exhibit insufficient understanding of visually rich documents. In this work, we propose jina-clip-v2, a contrastive vision-language model trained o","authors_text":"Andreas Koukounas, Bo Wang, Georgios Mastrapas, Han Xiao, Isabelle Mohr, Michael G\\\"unther, Mohammad Kalim Akram, Nan Wang, Saba Sturua, Sedigheh Eslami","cross_cats":["cs.CV","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T22:28:12Z","title":"jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08802","kind":"arxiv","version":2},"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":"sha256:70e1e4a2b0f058e19f6c8440900f775c076fa1f7a2bb73fb44a01232a7af9acb","target":"record","created_at":"2026-07-05T10:53:39Z","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":"62b7a1b49c381c3c12e21bcc8512a2d6a31cdb49b3932770b095511f9a172da8","cross_cats_sorted":["cs.CV","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T22:28:12Z","title_canon_sha256":"0bba5ea07adbd5e530fea0116c7ebb1c3bd33b4351d3b71659410af626456e7d"},"schema_version":"1.0","source":{"id":"2412.08802","kind":"arxiv","version":2}},"canonical_sha256":"8b9927e0da9a11e37d1a831664e3e4ce42fed1b1ae7d50f2e8a9978b5fe06445","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b9927e0da9a11e37d1a831664e3e4ce42fed1b1ae7d50f2e8a9978b5fe06445","first_computed_at":"2026-07-05T10:53:39.212310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:39.212310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2hgEKU2DDORdMJpPRz7B7690cRQOQoEzJR3FNj8RtQA9jxE0gRUgcYPkvQjOSGdh8aHziY1gffRXLkPQyMJmDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:39.212822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08802","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70e1e4a2b0f058e19f6c8440900f775c076fa1f7a2bb73fb44a01232a7af9acb","sha256:fedc014113d90f7b706df3a33d854c6035d07142c664a3b540e21ace07c48b30"],"state_sha256":"5988aaa35679787457dd03044c1bf367615068d6be3f5325c31a62ce554c4f25"}