{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VPRIFEC477XGEA2NIGFUFFO6YV","short_pith_number":"pith:VPRIFEC4","canonical_record":{"source":{"id":"2405.20204","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T16:07:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR"],"title_canon_sha256":"654a1314abdce96dbba9d83fc14cc7ba6e9981c550e05f6ca11c0691c2802e5a","abstract_canon_sha256":"4250b1c314083999839bfd17a09bd5c7a777198a75935e94a2914dc2122697ad"},"schema_version":"1.0"},"canonical_sha256":"abe282905cffee62034d418b4295dec566bd67aebe54788bf6bbefe15d6b7a28","source":{"kind":"arxiv","id":"2405.20204","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VPRIFEC477XGEA2NIGFUFFO6YV","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20204","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T16:07:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR"],"title_canon_sha256":"654a1314abdce96dbba9d83fc14cc7ba6e9981c550e05f6ca11c0691c2802e5a","abstract_canon_sha256":"4250b1c314083999839bfd17a09bd5c7a777198a75935e94a2914dc2122697ad"},"schema_version":"1.0"},"canonical_sha256":"abe282905cffee62034d418b4295dec566bd67aebe54788bf6bbefe15d6b7a28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:48.149917Z","signature_b64":"cBJeh7nu7xcXaYD+og9TKmPFX2kCbeBHGHTl1Ifs0TnsZMuRAjWewo5UfFD4WExc/JmuJLlJm5FBPIuHmMXUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abe282905cffee62034d418b4295dec566bd67aebe54788bf6bbefe15d6b7a28","last_reissued_at":"2026-07-05T08:36:48.149403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:48.149403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20204","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iVK1KyybxTA6mOztSBjCy2ScDGm6pAu5YtUFe6Q1c3yBjfT4cjYeLGp/uB9+LEUjhoVZ77oumlwAkLWR/tFVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:10:48.902242Z"},"content_sha256":"f7361d348da201bef67eabd98e351f4706a2d326bed54d92d71d23aee56463f6","schema_version":"1.0","event_id":"sha256:f7361d348da201bef67eabd98e351f4706a2d326bed54d92d71d23aee56463f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VPRIFEC477XGEA2NIGFUFFO6YV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jina CLIP: Your CLIP Model Is Also Your Text Retriever","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR"],"primary_cat":"cs.CL","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","submitted_at":"2024-05-30T16:07:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20204","kind":"arxiv","version":2},"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/2405.20204/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOs2FIZv9zVDZEGaJkNKX5rGDPgQlVVZ/KwKEYNr1AkCfQIwolFAFS45uEOuXw+Ndo+IVG7MMxqbUGZRGzNnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:10:48.903155Z"},"content_sha256":"0c535242db437d974f36d3faa6914625403df0e8709b41d76fcbcacba87e1b2e","schema_version":"1.0","event_id":"sha256:0c535242db437d974f36d3faa6914625403df0e8709b41d76fcbcacba87e1b2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPRIFEC477XGEA2NIGFUFFO6YV/bundle.json","state_url":"https://pith.science/pith/VPRIFEC477XGEA2NIGFUFFO6YV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPRIFEC477XGEA2NIGFUFFO6YV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T09:10:48Z","links":{"resolver":"https://pith.science/pith/VPRIFEC477XGEA2NIGFUFFO6YV","bundle":"https://pith.science/pith/VPRIFEC477XGEA2NIGFUFFO6YV/bundle.json","state":"https://pith.science/pith/VPRIFEC477XGEA2NIGFUFFO6YV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPRIFEC477XGEA2NIGFUFFO6YV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+2BhRfGjkVW4I4/4HysYYjtj8ZhZ2HSQhivZlioWR+hDyvVf8YRNbqUHXGsToYuM6+g9ZcMaQHr+V/i5LXQNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:10:48.909623Z","bundle_sha256":"5ace55ecdcd4e4081995ce239aa16c119fdaa9a24215770d5c22043476f6f104"}}