{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IGAE2QRLTB5VAP66KPJDWNZYI4","short_pith_number":"pith:IGAE2QRL","schema_version":"1.0","canonical_sha256":"41804d422b987b503fde53d23b37384719bf1c5d97d2ac9d64da63af491f6db7","source":{"kind":"arxiv","id":"2406.13718","version":2},"attestation_state":"computed","paper":{"title":"Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Yarowsky, Kenton Murray, Niyati Bafna","submitted_at":"2024-06-19T17:20:28Z","abstract_excerpt":"While large language models exhibit certain cross-lingual generalization capabilities, they suffer from performance degradation (PD) on unseen closely-related languages (CRLs) and dialects relative to their high-resource language neighbour (HRLN). However, we currently lack a fundamental understanding of what kinds of linguistic distances contribute to PD, and to what extent. Furthermore, studies of cross-lingual generalization are confounded by unknown quantities of CRL language traces in the training data, and by the frequent lack of availability of evaluation data in lower-resource related "},"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":"2406.13718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T17:20:28Z","cross_cats_sorted":[],"title_canon_sha256":"d0f242f7a5bf40b013b3e06c1f0ce14750ce1bd7f5297a125640348499f04395","abstract_canon_sha256":"86b15d763f9f1afc5dbf1bb8ca72cf81c472e4ff1c3cf586d851f95bfd393625"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:04.610822Z","signature_b64":"/uyVrdwrVidHlrd1GoOwOLHquKlXTRcETonB3R/82bcGYDtekHcCX/dFKvfD9j6lguPefzdjI1reu5krlLaQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41804d422b987b503fde53d23b37384719bf1c5d97d2ac9d64da63af491f6db7","last_reissued_at":"2026-07-05T10:06:04.610337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:04.610337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Yarowsky, Kenton Murray, Niyati Bafna","submitted_at":"2024-06-19T17:20:28Z","abstract_excerpt":"While large language models exhibit certain cross-lingual generalization capabilities, they suffer from performance degradation (PD) on unseen closely-related languages (CRLs) and dialects relative to their high-resource language neighbour (HRLN). However, we currently lack a fundamental understanding of what kinds of linguistic distances contribute to PD, and to what extent. Furthermore, studies of cross-lingual generalization are confounded by unknown quantities of CRL language traces in the training data, and by the frequent lack of availability of evaluation data in lower-resource related "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13718","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/2406.13718/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":"2406.13718","created_at":"2026-07-05T10:06:04.610389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13718v2","created_at":"2026-07-05T10:06:04.610389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13718","created_at":"2026-07-05T10:06:04.610389+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGAE2QRLTB5V","created_at":"2026-07-05T10:06:04.610389+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGAE2QRLTB5VAP66","created_at":"2026-07-05T10:06:04.610389+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGAE2QRL","created_at":"2026-07-05T10:06:04.610389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4","json":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4.json","graph_json":"https://pith.science/api/pith-number/IGAE2QRLTB5VAP66KPJDWNZYI4/graph.json","events_json":"https://pith.science/api/pith-number/IGAE2QRLTB5VAP66KPJDWNZYI4/events.json","paper":"https://pith.science/paper/IGAE2QRL"},"agent_actions":{"view_html":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4","download_json":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4.json","view_paper":"https://pith.science/paper/IGAE2QRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13718&json=true","fetch_graph":"https://pith.science/api/pith-number/IGAE2QRLTB5VAP66KPJDWNZYI4/graph.json","fetch_events":"https://pith.science/api/pith-number/IGAE2QRLTB5VAP66KPJDWNZYI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4/action/storage_attestation","attest_author":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4/action/author_attestation","sign_citation":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4/action/citation_signature","submit_replication":"https://pith.science/pith/IGAE2QRLTB5VAP66KPJDWNZYI4/action/replication_record"}},"created_at":"2026-07-05T10:06:04.610389+00:00","updated_at":"2026-07-05T10:06:04.610389+00:00"}