{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CIUDRT5YBPVON33VZQUQYPLKPG","short_pith_number":"pith:CIUDRT5Y","schema_version":"1.0","canonical_sha256":"122838cfb80beae6ef75cc290c3d6a79b6a7cd1183aa834078ee09d9e6342a24","source":{"kind":"arxiv","id":"2303.16145","version":1},"attestation_state":"computed","paper":{"title":"NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","submitted_at":"2023-03-28T17:10:48Z","abstract_excerpt":"This paper reports on a study of cross-lingual information retrieval (CLIR) using the mT5-XXL reranker on the NeuCLIR track of TREC 2022. Perhaps the biggest contribution of this study is the finding that despite the mT5 model being fine-tuned only on query-document pairs of the same language it proved to be viable for CLIR tasks, where query-document pairs are in different languages, even in the presence of suboptimal first-stage retrieval performance. The results of the study show outstanding performance across all tasks and languages, leading to a high number of winning positions. Finally, "},"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":"2303.16145","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-28T17:10:48Z","cross_cats_sorted":[],"title_canon_sha256":"19de97abfb30a4c9fb8cc329b9f890b2cdb9c2e168c91b2ed8ebb7eea482d9a0","abstract_canon_sha256":"5c39f081aa4fb113a0ea40c84e5d04c0c6837e738597f70d7a178ea3d15271e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:32.476668Z","signature_b64":"kHXMmD7u8Ug978TLHG7LfLapNpOg+xLAzu2JB9oJAF/h588j029a6Q2SChaSVEJociV0eETrQqlMIKFLBr5NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"122838cfb80beae6ef75cc290c3d6a79b6a7cd1183aa834078ee09d9e6342a24","last_reissued_at":"2026-07-05T05:55:32.476240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:32.476240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","submitted_at":"2023-03-28T17:10:48Z","abstract_excerpt":"This paper reports on a study of cross-lingual information retrieval (CLIR) using the mT5-XXL reranker on the NeuCLIR track of TREC 2022. Perhaps the biggest contribution of this study is the finding that despite the mT5 model being fine-tuned only on query-document pairs of the same language it proved to be viable for CLIR tasks, where query-document pairs are in different languages, even in the presence of suboptimal first-stage retrieval performance. The results of the study show outstanding performance across all tasks and languages, leading to a high number of winning positions. Finally, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16145","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/2303.16145/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":"2303.16145","created_at":"2026-07-05T05:55:32.476331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16145v1","created_at":"2026-07-05T05:55:32.476331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16145","created_at":"2026-07-05T05:55:32.476331+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIUDRT5YBPVO","created_at":"2026-07-05T05:55:32.476331+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIUDRT5YBPVON33V","created_at":"2026-07-05T05:55:32.476331+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIUDRT5Y","created_at":"2026-07-05T05:55:32.476331+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26352","citing_title":"RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG","json":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG.json","graph_json":"https://pith.science/api/pith-number/CIUDRT5YBPVON33VZQUQYPLKPG/graph.json","events_json":"https://pith.science/api/pith-number/CIUDRT5YBPVON33VZQUQYPLKPG/events.json","paper":"https://pith.science/paper/CIUDRT5Y"},"agent_actions":{"view_html":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG","download_json":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG.json","view_paper":"https://pith.science/paper/CIUDRT5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16145&json=true","fetch_graph":"https://pith.science/api/pith-number/CIUDRT5YBPVON33VZQUQYPLKPG/graph.json","fetch_events":"https://pith.science/api/pith-number/CIUDRT5YBPVON33VZQUQYPLKPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG/action/storage_attestation","attest_author":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG/action/author_attestation","sign_citation":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG/action/citation_signature","submit_replication":"https://pith.science/pith/CIUDRT5YBPVON33VZQUQYPLKPG/action/replication_record"}},"created_at":"2026-07-05T05:55:32.476331+00:00","updated_at":"2026-07-05T05:55:32.476331+00:00"}