{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DFB6NFVWHLLO3KOARSGEKYIWOO","short_pith_number":"pith:DFB6NFVW","schema_version":"1.0","canonical_sha256":"1943e696b63ad6eda9c08c8c45611673a6ce6aaa881c707eda493f0dcb9aec31","source":{"kind":"arxiv","id":"2405.11125","version":1},"attestation_state":"computed","paper":{"title":"A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A. Seza Do\\u{g}ru\\\"oz, En-Shiun Annie Lee, Eric Khiu, Guo Qing Huai, Hasti Toossi, Jinyu Liu","submitted_at":"2024-05-17T23:53:48Z","abstract_excerpt":"In the pursuit of supporting more languages around the world, tools that characterize properties of languages play a key role in expanding the existing multilingual NLP research. In this study, we focus on a widely used typological knowledge base, URIEL, which aggregates linguistic information into numeric vectors. Specifically, we delve into the soundness and reproducibility of the approach taken by URIEL in quantifying language similarity. Our analysis reveals URIEL's ambiguity in calculating language distances and in handling missing values. Moreover, we find that URIEL does not provide any"},"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":"2405.11125","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-17T23:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"e606f2dc1c079cfcb023cbcfb8dfbf33c6410087e757b62d80fcae649c97dc06","abstract_canon_sha256":"b9ef06b7ae34590d345d2f77573c744f45d42aff83d91ccc70c1e1400e63ab04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:33.636396Z","signature_b64":"B3/F/AkTQbr7jiM4eWviOO01JkZAWeIZQrtdepVBuDYwBLztqayv3gPFKAfN8mgl4T5v+0l1Jp7+pOeaCAOPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1943e696b63ad6eda9c08c8c45611673a6ce6aaa881c707eda493f0dcb9aec31","last_reissued_at":"2026-07-05T08:20:33.635906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:33.635906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A. Seza Do\\u{g}ru\\\"oz, En-Shiun Annie Lee, Eric Khiu, Guo Qing Huai, Hasti Toossi, Jinyu Liu","submitted_at":"2024-05-17T23:53:48Z","abstract_excerpt":"In the pursuit of supporting more languages around the world, tools that characterize properties of languages play a key role in expanding the existing multilingual NLP research. In this study, we focus on a widely used typological knowledge base, URIEL, which aggregates linguistic information into numeric vectors. Specifically, we delve into the soundness and reproducibility of the approach taken by URIEL in quantifying language similarity. Our analysis reveals URIEL's ambiguity in calculating language distances and in handling missing values. Moreover, we find that URIEL does not provide any"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11125","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/2405.11125/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":"2405.11125","created_at":"2026-07-05T08:20:33.635965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11125v1","created_at":"2026-07-05T08:20:33.635965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11125","created_at":"2026-07-05T08:20:33.635965+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFB6NFVWHLLO","created_at":"2026-07-05T08:20:33.635965+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFB6NFVWHLLO3KOA","created_at":"2026-07-05T08:20:33.635965+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFB6NFVW","created_at":"2026-07-05T08:20:33.635965+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/DFB6NFVWHLLO3KOARSGEKYIWOO","json":"https://pith.science/pith/DFB6NFVWHLLO3KOARSGEKYIWOO.json","graph_json":"https://pith.science/api/pith-number/DFB6NFVWHLLO3KOARSGEKYIWOO/graph.json","events_json":"https://pith.science/api/pith-number/DFB6NFVWHLLO3KOARSGEKYIWOO/events.json","paper":"https://pith.science/paper/DFB6NFVW"},"agent_actions":{"view_html":"https://pith.science/pith/DFB6NFVWHLLO3KOARSGEKYIWOO","download_json":"https://pith.science/pith/DFB6NFVWHLLO3KOARSGEKYIWOO.json","view_paper":"https://pith.science/paper/DFB6NFVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11125&json=true","fetch_graph":"https://pith.science/api/pith-number/DFB6NFVWHLLO3KOARSGEKYIWOO/graph.json","fetch_events":"https://pith.science/api/pith-number/DFB6NFVWHLLO3KOARSGEKYIWOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFB6NFVWHLLO3KOARSGEKYIWOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFB6NFVWHLLO3KOARSGEKYIWOO/action/storage_attestation","attest_author":"https://pith.science/pith/DFB6NFVWHLLO3KOARSGEKYIWOO/action/author_attestation","sign_citation":"https://pith.science/pith/DFB6NFVWHLLO3KOARSGEKYIWOO/action/citation_signature","submit_replication":"https://pith.science/pith/DFB6NFVWHLLO3KOARSGEKYIWOO/action/replication_record"}},"created_at":"2026-07-05T08:20:33.635965+00:00","updated_at":"2026-07-05T08:20:33.635965+00:00"}