{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BGVFZC7IDUHJZGPQOINZ3PETAX","short_pith_number":"pith:BGVFZC7I","schema_version":"1.0","canonical_sha256":"09aa5c8be81d0e9c99f0721b9dbc9305f77f805387b604634a8f2d13df81241e","source":{"kind":"arxiv","id":"2208.13078","version":1},"attestation_state":"computed","paper":{"title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ernie Chang, Jidong Ge, Pengke Chen, Qingyu Zhang, Xiaoyu Shen","submitted_at":"2022-08-27T19:35:20Z","abstract_excerpt":"Owing to the lack of corpora for low-resource languages, current works on dialogue generation have mainly focused on English. In this paper, we present mDIA, the first large-scale multilingual benchmark for dialogue generation across low- to high-resource languages. It covers real-life conversations in 46 languages across 19 language families. We present baseline results obtained by fine-tuning the multilingual, non-dialogue-focused pre-trained model mT5 as well as English-centric, dialogue-focused pre-trained chatbot DialoGPT. The results show that mT5-based models perform better on sacreBLEU"},"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":"2208.13078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-27T19:35:20Z","cross_cats_sorted":[],"title_canon_sha256":"c69486f8ae15f5098e26ec6af13d19e0cc8f38e81b4b9d64a134c596e81f6b31","abstract_canon_sha256":"e23899ab99ac1f0da3e726236cb2e416d7381ff1677a1a7e2c57f6c7723efd8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:52:03.133778Z","signature_b64":"FWanmbEXWIObv4FoFHMwoAb58x3uGo+JrTCiE44kVSajA//mOvx7tFoWRSnhRTGK2WFUgiZ2oRb8h4t1ikDjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09aa5c8be81d0e9c99f0721b9dbc9305f77f805387b604634a8f2d13df81241e","last_reissued_at":"2026-07-05T04:52:03.133202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:52:03.133202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ernie Chang, Jidong Ge, Pengke Chen, Qingyu Zhang, Xiaoyu Shen","submitted_at":"2022-08-27T19:35:20Z","abstract_excerpt":"Owing to the lack of corpora for low-resource languages, current works on dialogue generation have mainly focused on English. In this paper, we present mDIA, the first large-scale multilingual benchmark for dialogue generation across low- to high-resource languages. It covers real-life conversations in 46 languages across 19 language families. We present baseline results obtained by fine-tuning the multilingual, non-dialogue-focused pre-trained model mT5 as well as English-centric, dialogue-focused pre-trained chatbot DialoGPT. The results show that mT5-based models perform better on sacreBLEU"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13078","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/2208.13078/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":"2208.13078","created_at":"2026-07-05T04:52:03.133312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.13078v1","created_at":"2026-07-05T04:52:03.133312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13078","created_at":"2026-07-05T04:52:03.133312+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGVFZC7IDUHJ","created_at":"2026-07-05T04:52:03.133312+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGVFZC7IDUHJZGPQ","created_at":"2026-07-05T04:52:03.133312+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGVFZC7I","created_at":"2026-07-05T04:52:03.133312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07455","citing_title":"RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX","json":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX.json","graph_json":"https://pith.science/api/pith-number/BGVFZC7IDUHJZGPQOINZ3PETAX/graph.json","events_json":"https://pith.science/api/pith-number/BGVFZC7IDUHJZGPQOINZ3PETAX/events.json","paper":"https://pith.science/paper/BGVFZC7I"},"agent_actions":{"view_html":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX","download_json":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX.json","view_paper":"https://pith.science/paper/BGVFZC7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.13078&json=true","fetch_graph":"https://pith.science/api/pith-number/BGVFZC7IDUHJZGPQOINZ3PETAX/graph.json","fetch_events":"https://pith.science/api/pith-number/BGVFZC7IDUHJZGPQOINZ3PETAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX/action/storage_attestation","attest_author":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX/action/author_attestation","sign_citation":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX/action/citation_signature","submit_replication":"https://pith.science/pith/BGVFZC7IDUHJZGPQOINZ3PETAX/action/replication_record"}},"created_at":"2026-07-05T04:52:03.133312+00:00","updated_at":"2026-07-05T04:52:03.133312+00:00"}