{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JMI3EBPPU724TRM6P32VFVRMXV","short_pith_number":"pith:JMI3EBPP","schema_version":"1.0","canonical_sha256":"4b11b205efa7f5c9c59e7ef552d62cbd7ab2e8a6de19e0e2cd0e4246a04e410a","source":{"kind":"arxiv","id":"2301.06527","version":1},"attestation_state":"computed","paper":{"title":"XNLI 2.0: Improving XNLI dataset and performance on Cross Lingual Understanding (XLU)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankit Kumar Upadhyay, Harsit Kumar Upadhya","submitted_at":"2023-01-16T17:24:57Z","abstract_excerpt":"Natural Language Processing systems are heavily dependent on the availability of annotated data to train practical models. Primarily, models are trained on English datasets. In recent times, significant advances have been made in multilingual understanding due to the steeply increasing necessity of working in different languages. One of the points that stands out is that since there are now so many pre-trained multilingual models, we can utilize them for cross-lingual understanding tasks. Using cross-lingual understanding and Natural Language Inference, it is possible to train models whose app"},"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":"2301.06527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-16T17:24:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"259f7f788c4535a5a163fc67611cc68648eef0c916bca30d3a07b1295c9a254f","abstract_canon_sha256":"6698ec596b7c24462aa4cfa2ac684efaf821a7ec482eef6d289d09eb7e0c9823"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:32.939960Z","signature_b64":"i1q01Wi1V+SmdiEjZw4qcVK0n/cyRdoopHrXzykfv0OY7FEWkcCrxOOl++IQBlmxRDmgrYOTP2YJ3p6i+O+ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b11b205efa7f5c9c59e7ef552d62cbd7ab2e8a6de19e0e2cd0e4246a04e410a","last_reissued_at":"2026-07-05T05:33:32.939328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:32.939328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XNLI 2.0: Improving XNLI dataset and performance on Cross Lingual Understanding (XLU)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankit Kumar Upadhyay, Harsit Kumar Upadhya","submitted_at":"2023-01-16T17:24:57Z","abstract_excerpt":"Natural Language Processing systems are heavily dependent on the availability of annotated data to train practical models. Primarily, models are trained on English datasets. In recent times, significant advances have been made in multilingual understanding due to the steeply increasing necessity of working in different languages. One of the points that stands out is that since there are now so many pre-trained multilingual models, we can utilize them for cross-lingual understanding tasks. Using cross-lingual understanding and Natural Language Inference, it is possible to train models whose app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06527","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/2301.06527/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":"2301.06527","created_at":"2026-07-05T05:33:32.939391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06527v1","created_at":"2026-07-05T05:33:32.939391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06527","created_at":"2026-07-05T05:33:32.939391+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMI3EBPPU724","created_at":"2026-07-05T05:33:32.939391+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMI3EBPPU724TRM6","created_at":"2026-07-05T05:33:32.939391+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMI3EBPP","created_at":"2026-07-05T05:33:32.939391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.16606","citing_title":"Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV","json":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV.json","graph_json":"https://pith.science/api/pith-number/JMI3EBPPU724TRM6P32VFVRMXV/graph.json","events_json":"https://pith.science/api/pith-number/JMI3EBPPU724TRM6P32VFVRMXV/events.json","paper":"https://pith.science/paper/JMI3EBPP"},"agent_actions":{"view_html":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV","download_json":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV.json","view_paper":"https://pith.science/paper/JMI3EBPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06527&json=true","fetch_graph":"https://pith.science/api/pith-number/JMI3EBPPU724TRM6P32VFVRMXV/graph.json","fetch_events":"https://pith.science/api/pith-number/JMI3EBPPU724TRM6P32VFVRMXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV/action/storage_attestation","attest_author":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV/action/author_attestation","sign_citation":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV/action/citation_signature","submit_replication":"https://pith.science/pith/JMI3EBPPU724TRM6P32VFVRMXV/action/replication_record"}},"created_at":"2026-07-05T05:33:32.939391+00:00","updated_at":"2026-07-05T05:33:32.939391+00:00"}