{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HFEA623ES327VYVFLCORDSD6Q2","short_pith_number":"pith:HFEA623E","schema_version":"1.0","canonical_sha256":"39480f6b6496f5fae2a5589d11c87e868b128420d04dfabaafb1454317b246aa","source":{"kind":"arxiv","id":"1809.05053","version":1},"attestation_state":"computed","paper":{"title":"XNLI: Evaluating Cross-lingual Sentence Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adina Williams, Alexis Conneau, Guillaume Lample, Holger Schwenk, Ruty Rinott, Samuel R. Bowman, Veselin Stoyanov","submitted_at":"2018-09-13T16:39:53Z","abstract_excerpt":"State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models. These models are generally trained on data in a single language (usually English), and cannot be directly used beyond that language. Since collecting data in every language is not realistic, there has been a growing interest in cross-lingual language understanding (XLU) and low-resource cross-language transfer. In this work, we construct an evaluation set for XLU by extending the development and test sets of the Multi-Genre Natural Language Inference Corpus (MultiNL"},"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":"1809.05053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-13T16:39:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8f903bfef8c70ef69a1d5d4c7a90f527b7b8ea126df94a2bcd6dc5f05898e128","abstract_canon_sha256":"d69f6d23a0ff1a00cf7dacb4863a7bbaa6b0557c6ca9546ec265c737a21b7e06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:46.753676Z","signature_b64":"a0eo6zt6x3TYwUtD/jh8ZqRJTsrEHZYNa380B2E67s7BxFwIgMise1bithlsir2JY2OQd/7eRBiiTsXZYiPeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39480f6b6496f5fae2a5589d11c87e868b128420d04dfabaafb1454317b246aa","last_reissued_at":"2026-05-18T00:05:46.752849Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:46.752849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XNLI: Evaluating Cross-lingual Sentence Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adina Williams, Alexis Conneau, Guillaume Lample, Holger Schwenk, Ruty Rinott, Samuel R. Bowman, Veselin Stoyanov","submitted_at":"2018-09-13T16:39:53Z","abstract_excerpt":"State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models. These models are generally trained on data in a single language (usually English), and cannot be directly used beyond that language. Since collecting data in every language is not realistic, there has been a growing interest in cross-lingual language understanding (XLU) and low-resource cross-language transfer. In this work, we construct an evaluation set for XLU by extending the development and test sets of the Multi-Genre Natural Language Inference Corpus (MultiNL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05053","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":""},"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":"1809.05053","created_at":"2026-05-18T00:05:46.752985+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.05053v1","created_at":"2026-05-18T00:05:46.752985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05053","created_at":"2026-05-18T00:05:46.752985+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFEA623ES327","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFEA623ES327VYVF","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFEA623E","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2507.12720","citing_title":"FLEXITOKENS: Flexible Tokenization for Evolving Language Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":286,"is_internal_anchor":true},{"citing_arxiv_id":"2311.16867","citing_title":"The Falcon Series of Open Language Models","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":177,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2","json":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2.json","graph_json":"https://pith.science/api/pith-number/HFEA623ES327VYVFLCORDSD6Q2/graph.json","events_json":"https://pith.science/api/pith-number/HFEA623ES327VYVFLCORDSD6Q2/events.json","paper":"https://pith.science/paper/HFEA623E"},"agent_actions":{"view_html":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2","download_json":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2.json","view_paper":"https://pith.science/paper/HFEA623E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.05053&json=true","fetch_graph":"https://pith.science/api/pith-number/HFEA623ES327VYVFLCORDSD6Q2/graph.json","fetch_events":"https://pith.science/api/pith-number/HFEA623ES327VYVFLCORDSD6Q2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2/action/storage_attestation","attest_author":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2/action/author_attestation","sign_citation":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2/action/citation_signature","submit_replication":"https://pith.science/pith/HFEA623ES327VYVFLCORDSD6Q2/action/replication_record"}},"created_at":"2026-05-18T00:05:46.752985+00:00","updated_at":"2026-05-18T00:05:46.752985+00:00"}