{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YVGXWA2RPAWIJLDXSPREEDXLCP","short_pith_number":"pith:YVGXWA2R","schema_version":"1.0","canonical_sha256":"c54d7b0351782c84ac7793e2420eeb13d998c8a5a5cdf9900801469239804440","source":{"kind":"arxiv","id":"2401.04810","version":1},"attestation_state":"computed","paper":{"title":"Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Dawn Lawrie, Douglas W. Oard, Eugene Yang, James Mayfield, Scott Miller","submitted_at":"2024-01-09T20:40:49Z","abstract_excerpt":"Prior work on English monolingual retrieval has shown that a cross-encoder trained using a large number of relevance judgments for query-document pairs can be used as a teacher to train more efficient, but similarly effective, dual-encoder student models. Applying a similar knowledge distillation approach to training an efficient dual-encoder model for Cross-Language Information Retrieval (CLIR), where queries and documents are in different languages, is challenging due to the lack of a sufficiently large training collection when the query and document languages differ. The state of the art fo"},"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":"2401.04810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-01-09T20:40:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"46244dd67f3e0a7827c1cf2d48df13284d1b659c5cc0b3aca25e6eafcf8f2f40","abstract_canon_sha256":"752002b22511471dc9599124feb5e0fff73b6230dafa32370166d5b70b502931"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:58.641950Z","signature_b64":"9SC6Tz7cubmSDzlXaY2wiMBk0GwOaRxA/HN3VBV6Xi2fX88P6Y2rA3/2Lo5unMuCe6okDa8VlHdXOyfDx4GsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c54d7b0351782c84ac7793e2420eeb13d998c8a5a5cdf9900801469239804440","last_reissued_at":"2026-07-05T07:31:58.641547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:58.641547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Dawn Lawrie, Douglas W. Oard, Eugene Yang, James Mayfield, Scott Miller","submitted_at":"2024-01-09T20:40:49Z","abstract_excerpt":"Prior work on English monolingual retrieval has shown that a cross-encoder trained using a large number of relevance judgments for query-document pairs can be used as a teacher to train more efficient, but similarly effective, dual-encoder student models. Applying a similar knowledge distillation approach to training an efficient dual-encoder model for Cross-Language Information Retrieval (CLIR), where queries and documents are in different languages, is challenging due to the lack of a sufficiently large training collection when the query and document languages differ. The state of the art fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04810","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/2401.04810/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":"2401.04810","created_at":"2026-07-05T07:31:58.641604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04810v1","created_at":"2026-07-05T07:31:58.641604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04810","created_at":"2026-07-05T07:31:58.641604+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVGXWA2RPAWI","created_at":"2026-07-05T07:31:58.641604+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVGXWA2RPAWIJLDX","created_at":"2026-07-05T07:31:58.641604+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVGXWA2R","created_at":"2026-07-05T07:31:58.641604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.08819","citing_title":"Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP","json":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP.json","graph_json":"https://pith.science/api/pith-number/YVGXWA2RPAWIJLDXSPREEDXLCP/graph.json","events_json":"https://pith.science/api/pith-number/YVGXWA2RPAWIJLDXSPREEDXLCP/events.json","paper":"https://pith.science/paper/YVGXWA2R"},"agent_actions":{"view_html":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP","download_json":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP.json","view_paper":"https://pith.science/paper/YVGXWA2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04810&json=true","fetch_graph":"https://pith.science/api/pith-number/YVGXWA2RPAWIJLDXSPREEDXLCP/graph.json","fetch_events":"https://pith.science/api/pith-number/YVGXWA2RPAWIJLDXSPREEDXLCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP/action/storage_attestation","attest_author":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP/action/author_attestation","sign_citation":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP/action/citation_signature","submit_replication":"https://pith.science/pith/YVGXWA2RPAWIJLDXSPREEDXLCP/action/replication_record"}},"created_at":"2026-07-05T07:31:58.641604+00:00","updated_at":"2026-07-05T07:31:58.641604+00:00"}