{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KNP5RAXHZN5VGD4E4LHKW4EI5K","short_pith_number":"pith:KNP5RAXH","schema_version":"1.0","canonical_sha256":"535fd882e7cb7b530f84e2ceab7088eaabeabae7487723cdf161a1afdfaa47c2","source":{"kind":"arxiv","id":"2309.01859","version":3},"attestation_state":"computed","paper":{"title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Visheratin","submitted_at":"2023-09-04T23:26:11Z","abstract_excerpt":"Today, the exponential rise of large models developed by academic and industrial institutions with the help of massive computing resources raises the question of whether someone without access to such resources can make a valuable scientific contribution. To explore this, we tried to solve the challenging task of multilingual image retrieval having a limited budget of $1,000. As a result, we present NLLB-CLIP - CLIP model with a text encoder from the NLLB model. To train the model, we used an automatically created dataset of 106,246 good-quality images with captions in 201 languages derived fr"},"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":"2309.01859","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T23:26:11Z","cross_cats_sorted":[],"title_canon_sha256":"e31db62508331e2b8cd07649adccc9b01f042c10847dba31c309ec01c8257b0d","abstract_canon_sha256":"10f30fec6e32235dc79d9d63a7987f92da3c0a21c4ce33c872c853e0da75a28d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:12.113798Z","signature_b64":"xpvSavSFRTA0AJ6QImoez8mN3ex0UwIGKWwIFdJBaOdvXhdNV/SDsTN0NjrIFkpesiOwUNliTNTMANSUyeJmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"535fd882e7cb7b530f84e2ceab7088eaabeabae7487723cdf161a1afdfaa47c2","last_reissued_at":"2026-07-05T07:08:12.113301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:12.113301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Visheratin","submitted_at":"2023-09-04T23:26:11Z","abstract_excerpt":"Today, the exponential rise of large models developed by academic and industrial institutions with the help of massive computing resources raises the question of whether someone without access to such resources can make a valuable scientific contribution. To explore this, we tried to solve the challenging task of multilingual image retrieval having a limited budget of $1,000. As a result, we present NLLB-CLIP - CLIP model with a text encoder from the NLLB model. To train the model, we used an automatically created dataset of 106,246 good-quality images with captions in 201 languages derived fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01859","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/2309.01859/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":"2309.01859","created_at":"2026-07-05T07:08:12.113374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01859v3","created_at":"2026-07-05T07:08:12.113374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01859","created_at":"2026-07-05T07:08:12.113374+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNP5RAXHZN5V","created_at":"2026-07-05T07:08:12.113374+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNP5RAXHZN5VGD4E","created_at":"2026-07-05T07:08:12.113374+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNP5RAXH","created_at":"2026-07-05T07:08:12.113374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18029","citing_title":"What Matters for Grocery Product Retrieval with Open Source Vision Language Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22123","citing_title":"Multilingual Vision-Language Models, A Survey","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K","json":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K.json","graph_json":"https://pith.science/api/pith-number/KNP5RAXHZN5VGD4E4LHKW4EI5K/graph.json","events_json":"https://pith.science/api/pith-number/KNP5RAXHZN5VGD4E4LHKW4EI5K/events.json","paper":"https://pith.science/paper/KNP5RAXH"},"agent_actions":{"view_html":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K","download_json":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K.json","view_paper":"https://pith.science/paper/KNP5RAXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01859&json=true","fetch_graph":"https://pith.science/api/pith-number/KNP5RAXHZN5VGD4E4LHKW4EI5K/graph.json","fetch_events":"https://pith.science/api/pith-number/KNP5RAXHZN5VGD4E4LHKW4EI5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K/action/storage_attestation","attest_author":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K/action/author_attestation","sign_citation":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K/action/citation_signature","submit_replication":"https://pith.science/pith/KNP5RAXHZN5VGD4E4LHKW4EI5K/action/replication_record"}},"created_at":"2026-07-05T07:08:12.113374+00:00","updated_at":"2026-07-05T07:08:12.113374+00:00"}