{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UM3BUY52OOUKEKSTXMI7HEN3P5","short_pith_number":"pith:UM3BUY52","schema_version":"1.0","canonical_sha256":"a3361a63ba73a8a22a53bb11f391bb7f7bbba628200a9a3fb506e39b3506cd05","source":{"kind":"arxiv","id":"2201.08471","version":1},"attestation_state":"computed","paper":{"title":"Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models","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, Kenton Murray, Kevin Duh, Paul McNamee, Suraj Nair","submitted_at":"2022-01-20T22:11:38Z","abstract_excerpt":"The advent of transformer-based models such as BERT has led to the rise of neural ranking models. These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25. While monolingual retrieval tasks have benefited from large-scale training collections such as MS MARCO and advances in neural architectures, cross-language retrieval tasks have fallen behind these advancements. This paper introduces ColBERT-X, a generalization of the ColBERT multi-representation dense retrieval model that uses the XLM-RoBERTa (XLM-R) encoder to support "},"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":"2201.08471","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2022-01-20T22:11:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"22ba54c1f440387293b892be1c6582ecbce017e9d1cdd13be07165aadf3592b1","abstract_canon_sha256":"cc3648024fdbafc26b5aabac264a84c80cdccfad880d299d992b62281f68dde4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:46.687028Z","signature_b64":"Qwg67UgMkfzvdmNk5ILC9U+KLMvwex0hOJWgTf+dzJ0aLmc0xX1JAqKuOdLn76zDWlNezjiqeWIIs96/6TOADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3361a63ba73a8a22a53bb11f391bb7f7bbba628200a9a3fb506e39b3506cd05","last_reissued_at":"2026-07-05T03:51:46.686570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:46.686570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models","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, Kenton Murray, Kevin Duh, Paul McNamee, Suraj Nair","submitted_at":"2022-01-20T22:11:38Z","abstract_excerpt":"The advent of transformer-based models such as BERT has led to the rise of neural ranking models. These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25. While monolingual retrieval tasks have benefited from large-scale training collections such as MS MARCO and advances in neural architectures, cross-language retrieval tasks have fallen behind these advancements. This paper introduces ColBERT-X, a generalization of the ColBERT multi-representation dense retrieval model that uses the XLM-RoBERTa (XLM-R) encoder to support "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08471","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/2201.08471/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":"2201.08471","created_at":"2026-07-05T03:51:46.686631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08471v1","created_at":"2026-07-05T03:51:46.686631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08471","created_at":"2026-07-05T03:51:46.686631+00:00"},{"alias_kind":"pith_short_12","alias_value":"UM3BUY52OOUK","created_at":"2026-07-05T03:51:46.686631+00:00"},{"alias_kind":"pith_short_16","alias_value":"UM3BUY52OOUKEKST","created_at":"2026-07-05T03:51:46.686631+00:00"},{"alias_kind":"pith_short_8","alias_value":"UM3BUY52","created_at":"2026-07-05T03:51:46.686631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22356","citing_title":"HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5","json":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5.json","graph_json":"https://pith.science/api/pith-number/UM3BUY52OOUKEKSTXMI7HEN3P5/graph.json","events_json":"https://pith.science/api/pith-number/UM3BUY52OOUKEKSTXMI7HEN3P5/events.json","paper":"https://pith.science/paper/UM3BUY52"},"agent_actions":{"view_html":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5","download_json":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5.json","view_paper":"https://pith.science/paper/UM3BUY52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08471&json=true","fetch_graph":"https://pith.science/api/pith-number/UM3BUY52OOUKEKSTXMI7HEN3P5/graph.json","fetch_events":"https://pith.science/api/pith-number/UM3BUY52OOUKEKSTXMI7HEN3P5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5/action/storage_attestation","attest_author":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5/action/author_attestation","sign_citation":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5/action/citation_signature","submit_replication":"https://pith.science/pith/UM3BUY52OOUKEKSTXMI7HEN3P5/action/replication_record"}},"created_at":"2026-07-05T03:51:46.686631+00:00","updated_at":"2026-07-05T03:51:46.686631+00:00"}