{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:535KXSTNZJCTY4YOLZ7NNBKAFF","short_pith_number":"pith:535KXSTN","schema_version":"1.0","canonical_sha256":"eefaabca6dca453c730e5e7ed6854029745dfb64c97485892f13887c852125d2","source":{"kind":"arxiv","id":"2005.00333","version":2},"attestation_state":"computed","paper":{"title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Edoardo Maria Ponti, Goran Glava\\v{s}, Ivan Vuli\\'c, Olga Majewska, Qianchu Liu","submitted_at":"2020-05-01T12:22:33Z","abstract_excerpt":"In order to simulate human language capacity, natural language processing systems must be able to reason about the dynamics of everyday situations, including their possible causes and effects. Moreover, they should be able to generalise the acquired world knowledge to new languages, modulo cultural differences. Advances in machine reasoning and cross-lingual transfer depend on the availability of challenging evaluation benchmarks. Motivated by both demands, we introduce Cross-lingual Choice of Plausible Alternatives (XCOPA), a typologically diverse multilingual dataset for causal commonsense r"},"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":"2005.00333","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T12:22:33Z","cross_cats_sorted":[],"title_canon_sha256":"88e4db91d32c755c4599045fbbfdacfafc1ee366d240251b6db4c32d22df3dea","abstract_canon_sha256":"1ff748234b0ded8b9f4cee39c8dc3f177d796a12868ceddc28ebef07e1f9f3e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:19.391575Z","signature_b64":"NVYzGZBi3Z0D15cMMjxVR0uhoGpiNSUbui9/l3+7wo60dY9Rk65ICzlAJksXUzHPRwMpJLuSdrbb0INra7XZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eefaabca6dca453c730e5e7ed6854029745dfb64c97485892f13887c852125d2","last_reissued_at":"2026-07-05T01:46:19.391077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:19.391077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Edoardo Maria Ponti, Goran Glava\\v{s}, Ivan Vuli\\'c, Olga Majewska, Qianchu Liu","submitted_at":"2020-05-01T12:22:33Z","abstract_excerpt":"In order to simulate human language capacity, natural language processing systems must be able to reason about the dynamics of everyday situations, including their possible causes and effects. Moreover, they should be able to generalise the acquired world knowledge to new languages, modulo cultural differences. Advances in machine reasoning and cross-lingual transfer depend on the availability of challenging evaluation benchmarks. Motivated by both demands, we introduce Cross-lingual Choice of Plausible Alternatives (XCOPA), a typologically diverse multilingual dataset for causal commonsense r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00333","kind":"arxiv","version":2},"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/2005.00333/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":"2005.00333","created_at":"2026-07-05T01:46:19.391131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00333v2","created_at":"2026-07-05T01:46:19.391131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00333","created_at":"2026-07-05T01:46:19.391131+00:00"},{"alias_kind":"pith_short_12","alias_value":"535KXSTNZJCT","created_at":"2026-07-05T01:46:19.391131+00:00"},{"alias_kind":"pith_short_16","alias_value":"535KXSTNZJCTY4YO","created_at":"2026-07-05T01:46:19.391131+00:00"},{"alias_kind":"pith_short_8","alias_value":"535KXSTN","created_at":"2026-07-05T01:46:19.391131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":194,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02430","citing_title":"Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29128","citing_title":"Apertus LLM Family Expansion via Distillation and Quantization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09205","citing_title":"From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF","json":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF.json","graph_json":"https://pith.science/api/pith-number/535KXSTNZJCTY4YOLZ7NNBKAFF/graph.json","events_json":"https://pith.science/api/pith-number/535KXSTNZJCTY4YOLZ7NNBKAFF/events.json","paper":"https://pith.science/paper/535KXSTN"},"agent_actions":{"view_html":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF","download_json":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF.json","view_paper":"https://pith.science/paper/535KXSTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00333&json=true","fetch_graph":"https://pith.science/api/pith-number/535KXSTNZJCTY4YOLZ7NNBKAFF/graph.json","fetch_events":"https://pith.science/api/pith-number/535KXSTNZJCTY4YOLZ7NNBKAFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF/action/storage_attestation","attest_author":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF/action/author_attestation","sign_citation":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF/action/citation_signature","submit_replication":"https://pith.science/pith/535KXSTNZJCTY4YOLZ7NNBKAFF/action/replication_record"}},"created_at":"2026-07-05T01:46:19.391131+00:00","updated_at":"2026-07-05T01:46:19.391131+00:00"}