{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HA2AZADKQACGMJBWYSOJXUK63W","short_pith_number":"pith:HA2AZADK","schema_version":"1.0","canonical_sha256":"38340c806a8004662436c49c9bd15edd824bb259dc526ff6efd00f5efb7f33b6","source":{"kind":"arxiv","id":"2501.00874","version":3},"attestation_state":"computed","paper":{"title":"LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Franck Dernoncourt, Hieu Man, Nghia Trung Ngo, Ryan A. Rossi, Thien Huu Nguyen, Viet Dac Lai","submitted_at":"2025-01-01T15:43:07Z","abstract_excerpt":"Recent advancements in large language models (LLMs) based embedding models have established new state-of-the-art benchmarks for text embedding tasks, particularly in dense vector-based retrieval. However, these models predominantly focus on English, leaving multilingual embedding capabilities largely unexplored. To address this limitation, we present LUSIFER, a novel zero-shot approach that adapts LLM-based embedding models for multilingual tasks without requiring multilingual supervision. LUSIFER's architecture combines a multilingual encoder, serving as a language-universal learner, with an "},"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":"2501.00874","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-01T15:43:07Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"cd449ad62f7dc434b49203845d47e6fbde8772ddf1ab02db7f6a598b2e0003c0","abstract_canon_sha256":"9b2370ac5846dd58629176e9fd36643b426f041c6dcffb545d97b65458743fd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:03.512482Z","signature_b64":"fKunbDDZwgVLAplwoDy4RzGy40P5Alk/bIZzTeHqa9cFXnemThsFTilXNmawO2vOBuoTjTjbWeIeltKbENU9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38340c806a8004662436c49c9bd15edd824bb259dc526ff6efd00f5efb7f33b6","last_reissued_at":"2026-07-05T11:00:03.511966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:03.511966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Franck Dernoncourt, Hieu Man, Nghia Trung Ngo, Ryan A. Rossi, Thien Huu Nguyen, Viet Dac Lai","submitted_at":"2025-01-01T15:43:07Z","abstract_excerpt":"Recent advancements in large language models (LLMs) based embedding models have established new state-of-the-art benchmarks for text embedding tasks, particularly in dense vector-based retrieval. However, these models predominantly focus on English, leaving multilingual embedding capabilities largely unexplored. To address this limitation, we present LUSIFER, a novel zero-shot approach that adapts LLM-based embedding models for multilingual tasks without requiring multilingual supervision. LUSIFER's architecture combines a multilingual encoder, serving as a language-universal learner, with an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00874","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/2501.00874/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":"2501.00874","created_at":"2026-07-05T11:00:03.512030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00874v3","created_at":"2026-07-05T11:00:03.512030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00874","created_at":"2026-07-05T11:00:03.512030+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA2AZADKQACG","created_at":"2026-07-05T11:00:03.512030+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA2AZADKQACGMJBW","created_at":"2026-07-05T11:00:03.512030+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA2AZADK","created_at":"2026-07-05T11:00:03.512030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W","json":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W.json","graph_json":"https://pith.science/api/pith-number/HA2AZADKQACGMJBWYSOJXUK63W/graph.json","events_json":"https://pith.science/api/pith-number/HA2AZADKQACGMJBWYSOJXUK63W/events.json","paper":"https://pith.science/paper/HA2AZADK"},"agent_actions":{"view_html":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W","download_json":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W.json","view_paper":"https://pith.science/paper/HA2AZADK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00874&json=true","fetch_graph":"https://pith.science/api/pith-number/HA2AZADKQACGMJBWYSOJXUK63W/graph.json","fetch_events":"https://pith.science/api/pith-number/HA2AZADKQACGMJBWYSOJXUK63W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W/action/storage_attestation","attest_author":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W/action/author_attestation","sign_citation":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W/action/citation_signature","submit_replication":"https://pith.science/pith/HA2AZADKQACGMJBWYSOJXUK63W/action/replication_record"}},"created_at":"2026-07-05T11:00:03.512030+00:00","updated_at":"2026-07-05T11:00:03.512030+00:00"}