{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RWJVMMVWTB7C5WQMRG5TYNE3AO","short_pith_number":"pith:RWJVMMVW","schema_version":"1.0","canonical_sha256":"8d935632b6987e2eda0c89bb3c349b03af1d368c6aaea51867214912b362f5f6","source":{"kind":"arxiv","id":"2302.14723","version":1},"attestation_state":"computed","paper":{"title":"Extending English IR methods to multi-lingual IR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Carlos Lassance","submitted_at":"2023-02-28T16:32:38Z","abstract_excerpt":"This paper describes our participation in the 2023 WSDM CUP - MIRACL challenge. Via a combination of i) document translation; ii) multilingual SPLADE and Contriever; and iii) multilingual RankT5 and many other models, we were able to get first place in both the known and surprise languages tracks. Our strategy mostly revolved around getting the most diverse runs for the first stage and then throwing all possible reranking techniques. While this was not a first for many techniques, we had some things that we believe were never tried before, for example, we train the first SPLADE model that is e"},"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":"2302.14723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-28T16:32:38Z","cross_cats_sorted":[],"title_canon_sha256":"566a8e94b6d74341397a295402bdeb3cbe5c5a54757c789f362ba3d125dc0b40","abstract_canon_sha256":"965fae1a15e0456b16f2e758208797e501c6699fb1c63b57e325f7f93b15f633"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:49.007205Z","signature_b64":"G1wBoDViGxGp6GhOW4XMGtDYMy91F32MGeoeHjtBte7EpJ09Y2ysKlGYmzz7GEuezLTJyKh0Heo+PFs8R5+oBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d935632b6987e2eda0c89bb3c349b03af1d368c6aaea51867214912b362f5f6","last_reissued_at":"2026-07-05T05:46:49.006506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:49.006506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extending English IR methods to multi-lingual IR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Carlos Lassance","submitted_at":"2023-02-28T16:32:38Z","abstract_excerpt":"This paper describes our participation in the 2023 WSDM CUP - MIRACL challenge. Via a combination of i) document translation; ii) multilingual SPLADE and Contriever; and iii) multilingual RankT5 and many other models, we were able to get first place in both the known and surprise languages tracks. Our strategy mostly revolved around getting the most diverse runs for the first stage and then throwing all possible reranking techniques. While this was not a first for many techniques, we had some things that we believe were never tried before, for example, we train the first SPLADE model that is e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14723","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/2302.14723/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":"2302.14723","created_at":"2026-07-05T05:46:49.006736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14723v1","created_at":"2026-07-05T05:46:49.006736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14723","created_at":"2026-07-05T05:46:49.006736+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWJVMMVWTB7C","created_at":"2026-07-05T05:46:49.006736+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWJVMMVWTB7C5WQM","created_at":"2026-07-05T05:46:49.006736+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWJVMMVW","created_at":"2026-07-05T05:46:49.006736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21511","citing_title":"From Tokens to Concepts: Leveraging SAE for SPLADE","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21511","citing_title":"From Tokens to Concepts: Leveraging SAE for SPLADE","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO","json":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO.json","graph_json":"https://pith.science/api/pith-number/RWJVMMVWTB7C5WQMRG5TYNE3AO/graph.json","events_json":"https://pith.science/api/pith-number/RWJVMMVWTB7C5WQMRG5TYNE3AO/events.json","paper":"https://pith.science/paper/RWJVMMVW"},"agent_actions":{"view_html":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO","download_json":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO.json","view_paper":"https://pith.science/paper/RWJVMMVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14723&json=true","fetch_graph":"https://pith.science/api/pith-number/RWJVMMVWTB7C5WQMRG5TYNE3AO/graph.json","fetch_events":"https://pith.science/api/pith-number/RWJVMMVWTB7C5WQMRG5TYNE3AO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO/action/storage_attestation","attest_author":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO/action/author_attestation","sign_citation":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO/action/citation_signature","submit_replication":"https://pith.science/pith/RWJVMMVWTB7C5WQMRG5TYNE3AO/action/replication_record"}},"created_at":"2026-07-05T05:46:49.006736+00:00","updated_at":"2026-07-05T05:46:49.006736+00:00"}