{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6CA6C3474GDJBXXF67UVHFHM2D","short_pith_number":"pith:6CA6C347","schema_version":"1.0","canonical_sha256":"f081e16f9fe18690dee5f7e95394ecd0dfea85e9a1e6683f42e257eb62155d9d","source":{"kind":"arxiv","id":"2402.15059","version":1},"attestation_state":"computed","paper":{"title":"ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Antoine Louis, Gerasimos Spanakis, Gijs van Dijck, Vageesh Saxena","submitted_at":"2024-02-23T02:21:24Z","abstract_excerpt":"State-of-the-art neural retrievers predominantly focus on high-resource languages like English, which impedes their adoption in retrieval scenarios involving other languages. Current approaches circumvent the lack of high-quality labeled data in non-English languages by leveraging multilingual pretrained language models capable of cross-lingual transfer. However, these models require substantial task-specific fine-tuning across multiple languages, often perform poorly in languages with minimal representation in the pretraining corpus, and struggle to incorporate new languages after the pretrai"},"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":"2402.15059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T02:21:24Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"314944d4d32f078ca7dca91b9ac0cf9ad0580841383c8da8f9435055014f27b0","abstract_canon_sha256":"b433032afd09d5387007e90063573a486d223b76dc9cecf843a956c0b29caf03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:21.393494Z","signature_b64":"wWumn65g60qgmz02eCK5Yc1eEuf1e/cbhsyD+iQvx4prjLC8hlBJgLo1opLFnVED//m88tpBA/AdOc1AqDh/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f081e16f9fe18690dee5f7e95394ecd0dfea85e9a1e6683f42e257eb62155d9d","last_reissued_at":"2026-07-05T07:48:21.392955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:21.392955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Antoine Louis, Gerasimos Spanakis, Gijs van Dijck, Vageesh Saxena","submitted_at":"2024-02-23T02:21:24Z","abstract_excerpt":"State-of-the-art neural retrievers predominantly focus on high-resource languages like English, which impedes their adoption in retrieval scenarios involving other languages. Current approaches circumvent the lack of high-quality labeled data in non-English languages by leveraging multilingual pretrained language models capable of cross-lingual transfer. However, these models require substantial task-specific fine-tuning across multiple languages, often perform poorly in languages with minimal representation in the pretraining corpus, and struggle to incorporate new languages after the pretrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15059","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/2402.15059/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":"2402.15059","created_at":"2026-07-05T07:48:21.393015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15059v1","created_at":"2026-07-05T07:48:21.393015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15059","created_at":"2026-07-05T07:48:21.393015+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CA6C3474GDJ","created_at":"2026-07-05T07:48:21.393015+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CA6C3474GDJBXXF","created_at":"2026-07-05T07:48:21.393015+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CA6C347","created_at":"2026-07-05T07:48:21.393015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08329","citing_title":"BEIR-NL: Zero-shot Information Retrieval Benchmark for the Dutch Language","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D","json":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D.json","graph_json":"https://pith.science/api/pith-number/6CA6C3474GDJBXXF67UVHFHM2D/graph.json","events_json":"https://pith.science/api/pith-number/6CA6C3474GDJBXXF67UVHFHM2D/events.json","paper":"https://pith.science/paper/6CA6C347"},"agent_actions":{"view_html":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D","download_json":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D.json","view_paper":"https://pith.science/paper/6CA6C347","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15059&json=true","fetch_graph":"https://pith.science/api/pith-number/6CA6C3474GDJBXXF67UVHFHM2D/graph.json","fetch_events":"https://pith.science/api/pith-number/6CA6C3474GDJBXXF67UVHFHM2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D/action/storage_attestation","attest_author":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D/action/author_attestation","sign_citation":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D/action/citation_signature","submit_replication":"https://pith.science/pith/6CA6C3474GDJBXXF67UVHFHM2D/action/replication_record"}},"created_at":"2026-07-05T07:48:21.393015+00:00","updated_at":"2026-07-05T07:48:21.393015+00:00"}