{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5GZAW4MS7LL6N7YZGXZ7QDIDHD","short_pith_number":"pith:5GZAW4MS","schema_version":"1.0","canonical_sha256":"e9b20b7192fad7e6ff1935f3f80d0338c7fa7bbec833a43a635c522d5ebc5db0","source":{"kind":"arxiv","id":"2605.30107","version":1},"attestation_state":"computed","paper":{"title":"Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Anna Korhonen, Ej Zhou, Evgeniia Razumovskaia, Ivan Vuli\\'c, Songbo Hu, Xiaobin Wang, Yinhong Liu","submitted_at":"2026-05-28T15:47:09Z","abstract_excerpt":"Creating spoken dialogue datasets is methodologically challenging, and these challenges are amplified when the goal is to build multilingual, multi-parallel datasets at scale. This work introduces HEALTHDIAL, a large-scale, multilingual, and multi-parallel dataset for developing and evaluating retrieval-augmented generation (RAG)-based spoken dialogue systems. The dataset comprises 6,000 information-seeking dialogues (1,500 per language) grounded in trusted content from the World Health Organization (WHO) and 163 hours of user speech recorded from native speakers of diverse dialects across fou"},"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":"2605.30107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T15:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"d811b394c15af832843a8697ff15d8bffcec6f9c8cb00cbad19d6257edbf44bd","abstract_canon_sha256":"dfba909d7c9b843ae7a7dc9653fabd8de3758cbe9ddad30a08f0435516d3fb61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:10.035145Z","signature_b64":"4EUl66ZS3xE+tz8KbXAg3Lq7TCvDcWKRA5rlmdgMlmYe9RXSSmeelP5JmdxLhetjJnAysVKQ9Qd2MMnvA+DyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9b20b7192fad7e6ff1935f3f80d0338c7fa7bbec833a43a635c522d5ebc5db0","last_reissued_at":"2026-05-29T02:06:10.034783Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:10.034783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Anna Korhonen, Ej Zhou, Evgeniia Razumovskaia, Ivan Vuli\\'c, Songbo Hu, Xiaobin Wang, Yinhong Liu","submitted_at":"2026-05-28T15:47:09Z","abstract_excerpt":"Creating spoken dialogue datasets is methodologically challenging, and these challenges are amplified when the goal is to build multilingual, multi-parallel datasets at scale. This work introduces HEALTHDIAL, a large-scale, multilingual, and multi-parallel dataset for developing and evaluating retrieval-augmented generation (RAG)-based spoken dialogue systems. The dataset comprises 6,000 information-seeking dialogues (1,500 per language) grounded in trusted content from the World Health Organization (WHO) and 163 hours of user speech recorded from native speakers of diverse dialects across fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30107","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/2605.30107/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":"2605.30107","created_at":"2026-05-29T02:06:10.034841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30107v1","created_at":"2026-05-29T02:06:10.034841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30107","created_at":"2026-05-29T02:06:10.034841+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GZAW4MS7LL6","created_at":"2026-05-29T02:06:10.034841+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GZAW4MS7LL6N7YZ","created_at":"2026-05-29T02:06:10.034841+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GZAW4MS","created_at":"2026-05-29T02:06:10.034841+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/5GZAW4MS7LL6N7YZGXZ7QDIDHD","json":"https://pith.science/pith/5GZAW4MS7LL6N7YZGXZ7QDIDHD.json","graph_json":"https://pith.science/api/pith-number/5GZAW4MS7LL6N7YZGXZ7QDIDHD/graph.json","events_json":"https://pith.science/api/pith-number/5GZAW4MS7LL6N7YZGXZ7QDIDHD/events.json","paper":"https://pith.science/paper/5GZAW4MS"},"agent_actions":{"view_html":"https://pith.science/pith/5GZAW4MS7LL6N7YZGXZ7QDIDHD","download_json":"https://pith.science/pith/5GZAW4MS7LL6N7YZGXZ7QDIDHD.json","view_paper":"https://pith.science/paper/5GZAW4MS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30107&json=true","fetch_graph":"https://pith.science/api/pith-number/5GZAW4MS7LL6N7YZGXZ7QDIDHD/graph.json","fetch_events":"https://pith.science/api/pith-number/5GZAW4MS7LL6N7YZGXZ7QDIDHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GZAW4MS7LL6N7YZGXZ7QDIDHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GZAW4MS7LL6N7YZGXZ7QDIDHD/action/storage_attestation","attest_author":"https://pith.science/pith/5GZAW4MS7LL6N7YZGXZ7QDIDHD/action/author_attestation","sign_citation":"https://pith.science/pith/5GZAW4MS7LL6N7YZGXZ7QDIDHD/action/citation_signature","submit_replication":"https://pith.science/pith/5GZAW4MS7LL6N7YZGXZ7QDIDHD/action/replication_record"}},"created_at":"2026-05-29T02:06:10.034841+00:00","updated_at":"2026-05-29T02:06:10.034841+00:00"}