{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TEC32CILB7B2HNUCMROMHN4IZP","short_pith_number":"pith:TEC32CIL","schema_version":"1.0","canonical_sha256":"9905bd090b0fc3a3b682645cc3b788cbf32a498bf4354d6bc9a27773a55ed1d1","source":{"kind":"arxiv","id":"2509.09459","version":1},"attestation_state":"computed","paper":{"title":"Boosting Data Utilization for Multilingual Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Changhao Guan, Chao Huang, Fengran Mo, Jinan Xu, Kaiyu Huang, Xinyu Wang, Yufeng Chen, Zhenrui Yue","submitted_at":"2025-09-11T13:42:50Z","abstract_excerpt":"Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common practice is to fine-tune the dense retriever via contrastive learning, whose effectiveness highly relies on the quality of the negative sample and the efficacy of mini-batch data. Different from the existing studies that focus on developing sophisticated model architecture, we propose a method to boost data utilization for multilingual dense retrieval by obtainin"},"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":"2509.09459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-11T13:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"506cb71e9eeb695c9d914e5f1c9ab9371deef3a571214366e3d721b09caba8ba","abstract_canon_sha256":"fa936a55d73127be23718976463ed67dd9e910a1f353c660342cc1d14b6cbbbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:36.432008Z","signature_b64":"Iqii9PmOUFFQ/a3FFV+9Fqz25tnV/8RodLShvpLuzZpkTmzs5rGmEwz6exEs9Fqs1Obii/eZDSn3CX8Gh+8DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9905bd090b0fc3a3b682645cc3b788cbf32a498bf4354d6bc9a27773a55ed1d1","last_reissued_at":"2026-07-05T12:09:36.431500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:36.431500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Data Utilization for Multilingual Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Changhao Guan, Chao Huang, Fengran Mo, Jinan Xu, Kaiyu Huang, Xinyu Wang, Yufeng Chen, Zhenrui Yue","submitted_at":"2025-09-11T13:42:50Z","abstract_excerpt":"Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common practice is to fine-tune the dense retriever via contrastive learning, whose effectiveness highly relies on the quality of the negative sample and the efficacy of mini-batch data. Different from the existing studies that focus on developing sophisticated model architecture, we propose a method to boost data utilization for multilingual dense retrieval by obtainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09459","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/2509.09459/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":"2509.09459","created_at":"2026-07-05T12:09:36.431561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09459v1","created_at":"2026-07-05T12:09:36.431561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09459","created_at":"2026-07-05T12:09:36.431561+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEC32CILB7B2","created_at":"2026-07-05T12:09:36.431561+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEC32CILB7B2HNUC","created_at":"2026-07-05T12:09:36.431561+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEC32CIL","created_at":"2026-07-05T12:09:36.431561+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/TEC32CILB7B2HNUCMROMHN4IZP","json":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP.json","graph_json":"https://pith.science/api/pith-number/TEC32CILB7B2HNUCMROMHN4IZP/graph.json","events_json":"https://pith.science/api/pith-number/TEC32CILB7B2HNUCMROMHN4IZP/events.json","paper":"https://pith.science/paper/TEC32CIL"},"agent_actions":{"view_html":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP","download_json":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP.json","view_paper":"https://pith.science/paper/TEC32CIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09459&json=true","fetch_graph":"https://pith.science/api/pith-number/TEC32CILB7B2HNUCMROMHN4IZP/graph.json","fetch_events":"https://pith.science/api/pith-number/TEC32CILB7B2HNUCMROMHN4IZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/action/storage_attestation","attest_author":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/action/author_attestation","sign_citation":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/action/citation_signature","submit_replication":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/action/replication_record"}},"created_at":"2026-07-05T12:09:36.431561+00:00","updated_at":"2026-07-05T12:09:36.431561+00:00"}