{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VPRIFEC477XGEA2NIGFUFFO6YV","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":"4250b1c314083999839bfd17a09bd5c7a777198a75935e94a2914dc2122697ad","cross_cats_sorted":["cs.AI","cs.CV","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T16:07:54Z","title_canon_sha256":"654a1314abdce96dbba9d83fc14cc7ba6e9981c550e05f6ca11c0691c2802e5a"},"schema_version":"1.0","source":{"id":"2405.20204","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20204","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20204v2","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20204","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"VPRIFEC477XG","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"VPRIFEC477XGEA2N","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"VPRIFEC4","created_at":"2026-07-05T08:36:48Z"}],"graph_snapshots":[{"event_id":"sha256:0c535242db437d974f36d3faa6914625403df0e8709b41d76fcbcacba87e1b2e","target":"graph","created_at":"2026-07-05T08:36:48Z","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/2405.20204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) is widely used to train models to align images and texts in a common embedding space by mapping them to fixed-sized vectors. These models are key to multimodal information retrieval and related tasks. However, CLIP models generally underperform in text-only tasks compared to specialized text models. This creates inefficiencies for information retrieval systems that keep separate embeddings and models for text-only and multimodal tasks. We propose a novel, multi-task contrastive training method to address this issue, which we use to train the jina-c","authors_text":"Andreas Koukounas, Bo Wang, Georgios Mastrapas, Han Xiao, Isabelle Mohr, Joan Fontanals Mart\\'inez, Maximilian Werk, Michael G\\\"unther, Mohammad Kalim Akram, Nan Wang, Saahil Ognawala, Saba Sturua, Scott Martens, Susana Guzman","cross_cats":["cs.AI","cs.CV","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T16:07:54Z","title":"Jina CLIP: Your CLIP Model Is Also Your Text Retriever"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20204","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:f7361d348da201bef67eabd98e351f4706a2d326bed54d92d71d23aee56463f6","target":"record","created_at":"2026-07-05T08:36:48Z","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":"4250b1c314083999839bfd17a09bd5c7a777198a75935e94a2914dc2122697ad","cross_cats_sorted":["cs.AI","cs.CV","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T16:07:54Z","title_canon_sha256":"654a1314abdce96dbba9d83fc14cc7ba6e9981c550e05f6ca11c0691c2802e5a"},"schema_version":"1.0","source":{"id":"2405.20204","kind":"arxiv","version":2}},"canonical_sha256":"abe282905cffee62034d418b4295dec566bd67aebe54788bf6bbefe15d6b7a28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abe282905cffee62034d418b4295dec566bd67aebe54788bf6bbefe15d6b7a28","first_computed_at":"2026-07-05T08:36:48.149403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:48.149403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cBJeh7nu7xcXaYD+og9TKmPFX2kCbeBHGHTl1Ifs0TnsZMuRAjWewo5UfFD4WExc/JmuJLlJm5FBPIuHmMXUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:48.149917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20204","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7361d348da201bef67eabd98e351f4706a2d326bed54d92d71d23aee56463f6","sha256:0c535242db437d974f36d3faa6914625403df0e8709b41d76fcbcacba87e1b2e"],"state_sha256":"0bc74cfcb4e693b53125f89e2530575c6e852d25e715a493ec61e0ca7b4939ee"}