{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B5H55RVHOTIGBKVVJCW47SFFUY","short_pith_number":"pith:B5H55RVH","schema_version":"1.0","canonical_sha256":"0f4fdec6a774d060aab548adcfc8a5a63d48714cc134b173ec13f44dcf681333","source":{"kind":"arxiv","id":"2003.11080","version":5},"attestation_state":"computed","paper":{"title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Siddhant, Graham Neubig, Junjie Hu, Melvin Johnson, Orhan Firat, Sebastian Ruder","submitted_at":"2020-03-24T19:09:37Z","abstract_excerpt":"Much recent progress in applications of machine learning models to NLP has been driven by benchmarks that evaluate models across a wide variety of tasks. However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models, a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks is still missing. To this end, we introduce the Cross-lingual TRansfer Evaluation of Multilingual Encoders XTREME benchmark, a multi-task benchmark for evaluating the cross-lingual generalization c"},"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":"2003.11080","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-24T19:09:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d2cbb824fb44ae6da421a6425a493fcfd440769c956b6872352075a6816aa7b","abstract_canon_sha256":"e458486ca858c4a1ccdb959e078ffeff7427eb0f35cd337be2b7e77097e40e9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:32:58.101303Z","signature_b64":"+8OHYhVXViEMoeM1jF1Dxjt+L0w5T9ABqCtCfk/6JiX8QSsRp9W3GSpeVyb9rq9dO68d/0TZRDApTuO3DzU2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f4fdec6a774d060aab548adcfc8a5a63d48714cc134b173ec13f44dcf681333","last_reissued_at":"2026-07-05T01:32:58.100850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:32:58.100850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Siddhant, Graham Neubig, Junjie Hu, Melvin Johnson, Orhan Firat, Sebastian Ruder","submitted_at":"2020-03-24T19:09:37Z","abstract_excerpt":"Much recent progress in applications of machine learning models to NLP has been driven by benchmarks that evaluate models across a wide variety of tasks. However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models, a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks is still missing. To this end, we introduce the Cross-lingual TRansfer Evaluation of Multilingual Encoders XTREME benchmark, a multi-task benchmark for evaluating the cross-lingual generalization c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11080","kind":"arxiv","version":5},"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/2003.11080/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":"2003.11080","created_at":"2026-07-05T01:32:58.100909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11080v5","created_at":"2026-07-05T01:32:58.100909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11080","created_at":"2026-07-05T01:32:58.100909+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5H55RVHOTIG","created_at":"2026-07-05T01:32:58.100909+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5H55RVHOTIGBKVV","created_at":"2026-07-05T01:32:58.100909+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5H55RVH","created_at":"2026-07-05T01:32:58.100909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21645","citing_title":"Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models","ref_index":260,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19668","citing_title":"Code-Switching Reveals Language Anchoring in Multilingual LLMs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2102.04664","citing_title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13436","citing_title":"Pretraining Language Models with Subword Regularization: An Empirical Study of BPE Dropout in Low-Resource NLP","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06231","citing_title":"YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06231","citing_title":"YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04208","citing_title":"Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17843","citing_title":"Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY","json":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY.json","graph_json":"https://pith.science/api/pith-number/B5H55RVHOTIGBKVVJCW47SFFUY/graph.json","events_json":"https://pith.science/api/pith-number/B5H55RVHOTIGBKVVJCW47SFFUY/events.json","paper":"https://pith.science/paper/B5H55RVH"},"agent_actions":{"view_html":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY","download_json":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY.json","view_paper":"https://pith.science/paper/B5H55RVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11080&json=true","fetch_graph":"https://pith.science/api/pith-number/B5H55RVHOTIGBKVVJCW47SFFUY/graph.json","fetch_events":"https://pith.science/api/pith-number/B5H55RVHOTIGBKVVJCW47SFFUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY/action/storage_attestation","attest_author":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY/action/author_attestation","sign_citation":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY/action/citation_signature","submit_replication":"https://pith.science/pith/B5H55RVHOTIGBKVVJCW47SFFUY/action/replication_record"}},"created_at":"2026-07-05T01:32:58.100909+00:00","updated_at":"2026-07-05T01:32:58.100909+00:00"}