{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C7Z26UAYU3SLVAH6ZATLB3V67M","short_pith_number":"pith:C7Z26UAY","schema_version":"1.0","canonical_sha256":"17f3af5018a6e4ba80fec826b0eebefb23d001d69a7dc188dacf788d363a2a51","source":{"kind":"arxiv","id":"2310.12892","version":1},"attestation_state":"computed","paper":{"title":"A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Guchun Zhang, Han Zhou, Ignacio Iacobacci, Ivan Vuli\\'c, Milan Gritta, Moy Yuan, Songbo Hu","submitted_at":"2023-10-19T16:41:44Z","abstract_excerpt":"Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP. In this work, we take stock of and empirically analyse task performance disparities that exist between multilingual task-oriented dialogue (ToD) systems. We first define new quantitative measures of absolute and relative equivalence in system performance, capturing disparities across languages and within individual languages. Through a series of controlled experiments, we demonstrate that performance disparities depend on a number of factors: the nature of the T"},"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":"2310.12892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T16:41:44Z","cross_cats_sorted":[],"title_canon_sha256":"0d3e91c62f605f03e58628162f255ae27e223560467c1872a91ac6050b259946","abstract_canon_sha256":"94d34bb227a8c29178b0c1526e5b1979de0244131ccf1e99a91bb5d2a8073199"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:44.070303Z","signature_b64":"2qce5Z6/SIbkWH1Lyu8PFgTptVQNZn339NdbrGezpfoXHIwnP/Q9tUZuSZIvZ4qWyH3dnCS8BQH+WiERyz7+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17f3af5018a6e4ba80fec826b0eebefb23d001d69a7dc188dacf788d363a2a51","last_reissued_at":"2026-07-05T07:02:44.069870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:44.069870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Guchun Zhang, Han Zhou, Ignacio Iacobacci, Ivan Vuli\\'c, Milan Gritta, Moy Yuan, Songbo Hu","submitted_at":"2023-10-19T16:41:44Z","abstract_excerpt":"Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP. In this work, we take stock of and empirically analyse task performance disparities that exist between multilingual task-oriented dialogue (ToD) systems. We first define new quantitative measures of absolute and relative equivalence in system performance, capturing disparities across languages and within individual languages. Through a series of controlled experiments, we demonstrate that performance disparities depend on a number of factors: the nature of the T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12892","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/2310.12892/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":"2310.12892","created_at":"2026-07-05T07:02:44.069928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12892v1","created_at":"2026-07-05T07:02:44.069928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12892","created_at":"2026-07-05T07:02:44.069928+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7Z26UAYU3SL","created_at":"2026-07-05T07:02:44.069928+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7Z26UAYU3SLVAH6","created_at":"2026-07-05T07:02:44.069928+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7Z26UAY","created_at":"2026-07-05T07:02:44.069928+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/C7Z26UAYU3SLVAH6ZATLB3V67M","json":"https://pith.science/pith/C7Z26UAYU3SLVAH6ZATLB3V67M.json","graph_json":"https://pith.science/api/pith-number/C7Z26UAYU3SLVAH6ZATLB3V67M/graph.json","events_json":"https://pith.science/api/pith-number/C7Z26UAYU3SLVAH6ZATLB3V67M/events.json","paper":"https://pith.science/paper/C7Z26UAY"},"agent_actions":{"view_html":"https://pith.science/pith/C7Z26UAYU3SLVAH6ZATLB3V67M","download_json":"https://pith.science/pith/C7Z26UAYU3SLVAH6ZATLB3V67M.json","view_paper":"https://pith.science/paper/C7Z26UAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12892&json=true","fetch_graph":"https://pith.science/api/pith-number/C7Z26UAYU3SLVAH6ZATLB3V67M/graph.json","fetch_events":"https://pith.science/api/pith-number/C7Z26UAYU3SLVAH6ZATLB3V67M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7Z26UAYU3SLVAH6ZATLB3V67M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7Z26UAYU3SLVAH6ZATLB3V67M/action/storage_attestation","attest_author":"https://pith.science/pith/C7Z26UAYU3SLVAH6ZATLB3V67M/action/author_attestation","sign_citation":"https://pith.science/pith/C7Z26UAYU3SLVAH6ZATLB3V67M/action/citation_signature","submit_replication":"https://pith.science/pith/C7Z26UAYU3SLVAH6ZATLB3V67M/action/replication_record"}},"created_at":"2026-07-05T07:02:44.069928+00:00","updated_at":"2026-07-05T07:02:44.069928+00:00"}