{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N5VCEVFOLR6OF73JZ7RBFO7CKH","short_pith_number":"pith:N5VCEVFO","schema_version":"1.0","canonical_sha256":"6f6a2254ae5c7ce2ff69cfe212bbe251d34567ed8875761902fc1ce3bfd72d49","source":{"kind":"arxiv","id":"2508.07069","version":1},"attestation_state":"computed","paper":{"title":"SEADialogues: A Multilingual Culturally Grounded Multi-turn Dialogue Dataset on Southeast Asian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Aswin Candra, Ekapol Chuangsuwanich, Fajri Koto, Genta Indra Winata, Maxalmina Satria Kahfi, Muhammad Alif Al Hakim, Muhammad Dehan Al Kautsar, Peerat Limkonchotiwat","submitted_at":"2025-08-09T18:22:35Z","abstract_excerpt":"Although numerous datasets have been developed to support dialogue systems, most existing chit-chat datasets overlook the cultural nuances inherent in natural human conversations. To address this gap, we introduce SEADialogues, a culturally grounded dialogue dataset centered on Southeast Asia, a region with over 700 million people and immense cultural diversity. Our dataset features dialogues in eight languages from six Southeast Asian countries, many of which are low-resource despite having sizable speaker populations. To enhance cultural relevance and personalization, each dialogue includes "},"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":"2508.07069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-09T18:22:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2da38a19e0cd7385c5d55e09e3bf9704a03717993792030f35b3ce61f10497b5","abstract_canon_sha256":"f840d157ef69e9b4950c098e557f53da98bfba704b24ac1db9a7cdfc2b779928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:40.293371Z","signature_b64":"k5GQ+akuuKbB9uf52MX7hZn0vdhgVkxHStGG3u94DFO+f5VavjI56q7fD38VzRo13BObNXH0gQLR3sFOaD/fBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f6a2254ae5c7ce2ff69cfe212bbe251d34567ed8875761902fc1ce3bfd72d49","last_reissued_at":"2026-07-05T11:51:40.292872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:40.292872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEADialogues: A Multilingual Culturally Grounded Multi-turn Dialogue Dataset on Southeast Asian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Aswin Candra, Ekapol Chuangsuwanich, Fajri Koto, Genta Indra Winata, Maxalmina Satria Kahfi, Muhammad Alif Al Hakim, Muhammad Dehan Al Kautsar, Peerat Limkonchotiwat","submitted_at":"2025-08-09T18:22:35Z","abstract_excerpt":"Although numerous datasets have been developed to support dialogue systems, most existing chit-chat datasets overlook the cultural nuances inherent in natural human conversations. To address this gap, we introduce SEADialogues, a culturally grounded dialogue dataset centered on Southeast Asia, a region with over 700 million people and immense cultural diversity. Our dataset features dialogues in eight languages from six Southeast Asian countries, many of which are low-resource despite having sizable speaker populations. To enhance cultural relevance and personalization, each dialogue includes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07069","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/2508.07069/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":"2508.07069","created_at":"2026-07-05T11:51:40.292943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07069v1","created_at":"2026-07-05T11:51:40.292943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07069","created_at":"2026-07-05T11:51:40.292943+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5VCEVFOLR6O","created_at":"2026-07-05T11:51:40.292943+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5VCEVFOLR6OF73J","created_at":"2026-07-05T11:51:40.292943+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5VCEVFO","created_at":"2026-07-05T11:51:40.292943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24929","citing_title":"GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH","json":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH.json","graph_json":"https://pith.science/api/pith-number/N5VCEVFOLR6OF73JZ7RBFO7CKH/graph.json","events_json":"https://pith.science/api/pith-number/N5VCEVFOLR6OF73JZ7RBFO7CKH/events.json","paper":"https://pith.science/paper/N5VCEVFO"},"agent_actions":{"view_html":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH","download_json":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH.json","view_paper":"https://pith.science/paper/N5VCEVFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07069&json=true","fetch_graph":"https://pith.science/api/pith-number/N5VCEVFOLR6OF73JZ7RBFO7CKH/graph.json","fetch_events":"https://pith.science/api/pith-number/N5VCEVFOLR6OF73JZ7RBFO7CKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH/action/storage_attestation","attest_author":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH/action/author_attestation","sign_citation":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH/action/citation_signature","submit_replication":"https://pith.science/pith/N5VCEVFOLR6OF73JZ7RBFO7CKH/action/replication_record"}},"created_at":"2026-07-05T11:51:40.292943+00:00","updated_at":"2026-07-05T11:51:40.292943+00:00"}