{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BGVFZC7IDUHJZGPQOINZ3PETAX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e23899ab99ac1f0da3e726236cb2e416d7381ff1677a1a7e2c57f6c7723efd8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-27T19:35:20Z","title_canon_sha256":"c69486f8ae15f5098e26ec6af13d19e0cc8f38e81b4b9d64a134c596e81f6b31"},"schema_version":"1.0","source":{"id":"2208.13078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.13078","created_at":"2026-07-05T04:52:03Z"},{"alias_kind":"arxiv_version","alias_value":"2208.13078v1","created_at":"2026-07-05T04:52:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13078","created_at":"2026-07-05T04:52:03Z"},{"alias_kind":"pith_short_12","alias_value":"BGVFZC7IDUHJ","created_at":"2026-07-05T04:52:03Z"},{"alias_kind":"pith_short_16","alias_value":"BGVFZC7IDUHJZGPQ","created_at":"2026-07-05T04:52:03Z"},{"alias_kind":"pith_short_8","alias_value":"BGVFZC7I","created_at":"2026-07-05T04:52:03Z"}],"graph_snapshots":[{"event_id":"sha256:47422313c48c0b072211a5c66736b5d3d58d0815f7c7710b03f5924607de1593","target":"graph","created_at":"2026-07-05T04:52:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.13078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ernie Chang, Jidong Ge, Pengke Chen, Qingyu Zhang, Xiaoyu Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-27T19:35:20Z","title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13078","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bfa4fd0c1dcbe881d15e31bf9c6e4f2de8c5166e36b20616f4711ed17e938bcd","target":"record","created_at":"2026-07-05T04:52:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e23899ab99ac1f0da3e726236cb2e416d7381ff1677a1a7e2c57f6c7723efd8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-27T19:35:20Z","title_canon_sha256":"c69486f8ae15f5098e26ec6af13d19e0cc8f38e81b4b9d64a134c596e81f6b31"},"schema_version":"1.0","source":{"id":"2208.13078","kind":"arxiv","version":1}},"canonical_sha256":"09aa5c8be81d0e9c99f0721b9dbc9305f77f805387b604634a8f2d13df81241e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09aa5c8be81d0e9c99f0721b9dbc9305f77f805387b604634a8f2d13df81241e","first_computed_at":"2026-07-05T04:52:03.133202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:52:03.133202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FWanmbEXWIObv4FoFHMwoAb58x3uGo+JrTCiE44kVSajA//mOvx7tFoWRSnhRTGK2WFUgiZ2oRb8h4t1ikDjDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:52:03.133778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.13078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfa4fd0c1dcbe881d15e31bf9c6e4f2de8c5166e36b20616f4711ed17e938bcd","sha256:47422313c48c0b072211a5c66736b5d3d58d0815f7c7710b03f5924607de1593"],"state_sha256":"fa4dd659f37c2931fab35f5918dcbc104ede0abd4f73469ef1489bb3455c2af2"}