{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JEIWGAFDNUBZP36GC2MXMZFPKN","short_pith_number":"pith:JEIWGAFD","schema_version":"1.0","canonical_sha256":"49116300a36d0397efc616997664af5378eb5e55b45bd5c34cb8cf69443a8446","source":{"kind":"arxiv","id":"2210.09984","version":1},"attestation_state":"computed","paper":{"title":"Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"David Alfonso-Hermelo, Ehsan Kamalloo, Jimmy Lin, Mehdi Rezagholizadeh, Nandan Thakur, Odunayo Ogundepo, Qun Liu, Xiaoguang Li, Xinyu Zhang","submitted_at":"2022-10-18T16:47:18Z","abstract_excerpt":"MIRACL (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual dataset we have built for the WSDM 2023 Cup challenge that focuses on ad hoc retrieval across 18 different languages, which collectively encompass over three billion native speakers around the world. These languages have diverse typologies, originate from many different language families, and are associated with varying amounts of available resources -- including what researchers typically characterize as high-resource as well as low-resource languages. Our dataset is designed to support the creation "},"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":"2210.09984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-10-18T16:47:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8ca06cd9cb7b3568f8dfa94ddc8133da29062ad8fe78547c84217b83705dd445","abstract_canon_sha256":"49c9fd5586c971ba19e09081ddb6e66d52d3224cf56eef7bf5442bd4c7968d57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:01.543967Z","signature_b64":"gEN8HsnMKpn3Jo6Nk7/YcP+cqtVd++pqHjezUleucxmXnbDB4vSO6cOZufoiGGWaxmby+yMsRM8462n78qbTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49116300a36d0397efc616997664af5378eb5e55b45bd5c34cb8cf69443a8446","last_reissued_at":"2026-07-05T05:08:01.543621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:01.543621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"David Alfonso-Hermelo, Ehsan Kamalloo, Jimmy Lin, Mehdi Rezagholizadeh, Nandan Thakur, Odunayo Ogundepo, Qun Liu, Xiaoguang Li, Xinyu Zhang","submitted_at":"2022-10-18T16:47:18Z","abstract_excerpt":"MIRACL (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual dataset we have built for the WSDM 2023 Cup challenge that focuses on ad hoc retrieval across 18 different languages, which collectively encompass over three billion native speakers around the world. These languages have diverse typologies, originate from many different language families, and are associated with varying amounts of available resources -- including what researchers typically characterize as high-resource as well as low-resource languages. Our dataset is designed to support the creation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09984","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/2210.09984/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":"2210.09984","created_at":"2026-07-05T05:08:01.543675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09984v1","created_at":"2026-07-05T05:08:01.543675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09984","created_at":"2026-07-05T05:08:01.543675+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEIWGAFDNUBZ","created_at":"2026-07-05T05:08:01.543675+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEIWGAFDNUBZP36G","created_at":"2026-07-05T05:08:01.543675+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEIWGAFD","created_at":"2026-07-05T05:08:01.543675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22203","citing_title":"Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2510.07048","citing_title":"Search-R3: Unifying Reasoning and Embedding in Large Language Models","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11272","citing_title":"Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10380","citing_title":"Automatic Teller Machines for Offline E-cash","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN","json":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN.json","graph_json":"https://pith.science/api/pith-number/JEIWGAFDNUBZP36GC2MXMZFPKN/graph.json","events_json":"https://pith.science/api/pith-number/JEIWGAFDNUBZP36GC2MXMZFPKN/events.json","paper":"https://pith.science/paper/JEIWGAFD"},"agent_actions":{"view_html":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN","download_json":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN.json","view_paper":"https://pith.science/paper/JEIWGAFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09984&json=true","fetch_graph":"https://pith.science/api/pith-number/JEIWGAFDNUBZP36GC2MXMZFPKN/graph.json","fetch_events":"https://pith.science/api/pith-number/JEIWGAFDNUBZP36GC2MXMZFPKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN/action/storage_attestation","attest_author":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN/action/author_attestation","sign_citation":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN/action/citation_signature","submit_replication":"https://pith.science/pith/JEIWGAFDNUBZP36GC2MXMZFPKN/action/replication_record"}},"created_at":"2026-07-05T05:08:01.543675+00:00","updated_at":"2026-07-05T05:08:01.543675+00:00"}