{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T6K26LDMJSKUAMNGAKRLAQSTEO","short_pith_number":"pith:T6K26LDM","schema_version":"1.0","canonical_sha256":"9f95af2c6c4c954031a602a2b0425323a4750706fb6e3fc5d9adce08921915ca","source":{"kind":"arxiv","id":"2402.17016","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Andreas Koukounas, Bo Wang, Feng Wang, Georgios Mastrapas, Han Xiao, Isabelle Mohr, Jie Fu, Joan Fontanals Mart\\'inez, Markus Krimmel, Maximilian Werk, Michael G\\\"unther, Mohammad Kalim Akram, Nan Wang, Qi Liu, Saahil Ognawala, Saba Sturua, Susana Guzman, Vinit Ravishankar, Ziniu Yu","submitted_at":"2024-02-26T20:53:12Z","abstract_excerpt":"We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language. These models are capable of processing lengthy text inputs with up to 8192 tokens, making them highly versatile for a range of natural language processing tasks such as text retrieval, clustering, and semantic textual similarity (STS) calculations.\n  By focusing on bilingual models and introducing a unique multi-task learning objective, we have significantly improved the model performance on STS tasks, which outperforms the capabilities of existing mu"},"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":"2402.17016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T20:53:12Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d16da999fc9b7f4a73cf25c3457e376290af579d2e9bbe4163050b7ae9b3015f","abstract_canon_sha256":"9aa5062b8aeb9a0c50aa1443f19be4b7e70137bf3e1fe0f982b536d0537b9a7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:40.269000Z","signature_b64":"uxRr19M2dwAfRh2gi5eKc4jXxPCSYRxXowhdbV6I8XXhytdciVVWbzzxS7NNXkCUtI8wCrW2MOKhTxf1wKq9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f95af2c6c4c954031a602a2b0425323a4750706fb6e3fc5d9adce08921915ca","last_reissued_at":"2026-07-05T07:49:40.268352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:40.268352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Andreas Koukounas, Bo Wang, Feng Wang, Georgios Mastrapas, Han Xiao, Isabelle Mohr, Jie Fu, Joan Fontanals Mart\\'inez, Markus Krimmel, Maximilian Werk, Michael G\\\"unther, Mohammad Kalim Akram, Nan Wang, Qi Liu, Saahil Ognawala, Saba Sturua, Susana Guzman, Vinit Ravishankar, Ziniu Yu","submitted_at":"2024-02-26T20:53:12Z","abstract_excerpt":"We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language. These models are capable of processing lengthy text inputs with up to 8192 tokens, making them highly versatile for a range of natural language processing tasks such as text retrieval, clustering, and semantic textual similarity (STS) calculations.\n  By focusing on bilingual models and introducing a unique multi-task learning objective, we have significantly improved the model performance on STS tasks, which outperforms the capabilities of existing mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17016","kind":"arxiv","version":1},"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/2402.17016/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":"2402.17016","created_at":"2026-07-05T07:49:40.268437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17016v1","created_at":"2026-07-05T07:49:40.268437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17016","created_at":"2026-07-05T07:49:40.268437+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6K26LDMJSKU","created_at":"2026-07-05T07:49:40.268437+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6K26LDMJSKUAMNG","created_at":"2026-07-05T07:49:40.268437+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6K26LDM","created_at":"2026-07-05T07:49:40.268437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13111","citing_title":"M\\\"OVE: A Holistic LLM Benchmark for the German Public Sector","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21934","citing_title":"Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15547","citing_title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12572","citing_title":"LMEB: Long-horizon Memory Embedding Benchmark","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26483","citing_title":"Efficient Listwise Reranking with Compressed Document Representations","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO","json":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO.json","graph_json":"https://pith.science/api/pith-number/T6K26LDMJSKUAMNGAKRLAQSTEO/graph.json","events_json":"https://pith.science/api/pith-number/T6K26LDMJSKUAMNGAKRLAQSTEO/events.json","paper":"https://pith.science/paper/T6K26LDM"},"agent_actions":{"view_html":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO","download_json":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO.json","view_paper":"https://pith.science/paper/T6K26LDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17016&json=true","fetch_graph":"https://pith.science/api/pith-number/T6K26LDMJSKUAMNGAKRLAQSTEO/graph.json","fetch_events":"https://pith.science/api/pith-number/T6K26LDMJSKUAMNGAKRLAQSTEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO/action/storage_attestation","attest_author":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO/action/author_attestation","sign_citation":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO/action/citation_signature","submit_replication":"https://pith.science/pith/T6K26LDMJSKUAMNGAKRLAQSTEO/action/replication_record"}},"created_at":"2026-07-05T07:49:40.268437+00:00","updated_at":"2026-07-05T07:49:40.268437+00:00"}