{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VSPQGJLZYIK67NSXXZXCQV7XSJ","short_pith_number":"pith:VSPQGJLZ","schema_version":"1.0","canonical_sha256":"ac9f032579c215efb657be6e2857f79265a898be880e0981c7f277fa213e4932","source":{"kind":"arxiv","id":"2606.28715","version":1},"attestation_state":"computed","paper":{"title":"SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aulia Adila, Kittiphat Leesombatwathana, My Chiffon Nguyen, Patomporn Payoungkhamdee, Saksorn Ruangtanusak, Samuel Cahyawijaya, Vissuta Gunawan Lim","submitted_at":"2026-06-27T03:44:00Z","abstract_excerpt":"While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood despite its importance to sovereign AI. To fill this gap, we introduce SEATauBench, the first agent-focused evaluation framework for SEA sovereign AI. SeaTau adapts TauBench to five languages -- Mandarin, Vietnamese, Thai, Indonesian, and Filipino -- and evaluates agents across progressively localized settings that vary the language of user-agent interaction, tool specifications, and task domains. Across three recent models, we find that English a"},"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":"2606.28715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T03:44:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a0c250acb71033643b5bbecca71d538642d52f2bc838d0cbc15bf3a6c4d0bc4","abstract_canon_sha256":"26c168d178485dd5303b6221bbc11322e89f7bbc496f242ee13f202c12590cb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:49.009740Z","signature_b64":"m3L/DLYxHnGFMrhmXJGJqTOW3nkZf+5ezT1q0z1t+gHvj7WUOSVk8Bf86AU2U+vKByLlNMxrA4bjq8MkCH3dCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac9f032579c215efb657be6e2857f79265a898be880e0981c7f277fa213e4932","last_reissued_at":"2026-06-30T01:16:49.009238Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:49.009238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aulia Adila, Kittiphat Leesombatwathana, My Chiffon Nguyen, Patomporn Payoungkhamdee, Saksorn Ruangtanusak, Samuel Cahyawijaya, Vissuta Gunawan Lim","submitted_at":"2026-06-27T03:44:00Z","abstract_excerpt":"While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood despite its importance to sovereign AI. To fill this gap, we introduce SEATauBench, the first agent-focused evaluation framework for SEA sovereign AI. SeaTau adapts TauBench to five languages -- Mandarin, Vietnamese, Thai, Indonesian, and Filipino -- and evaluates agents across progressively localized settings that vary the language of user-agent interaction, tool specifications, and task domains. Across three recent models, we find that English a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28715","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/2606.28715/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":"2606.28715","created_at":"2026-06-30T01:16:49.009308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28715v1","created_at":"2026-06-30T01:16:49.009308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28715","created_at":"2026-06-30T01:16:49.009308+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSPQGJLZYIK6","created_at":"2026-06-30T01:16:49.009308+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSPQGJLZYIK67NSX","created_at":"2026-06-30T01:16:49.009308+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSPQGJLZ","created_at":"2026-06-30T01:16:49.009308+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/VSPQGJLZYIK67NSXXZXCQV7XSJ","json":"https://pith.science/pith/VSPQGJLZYIK67NSXXZXCQV7XSJ.json","graph_json":"https://pith.science/api/pith-number/VSPQGJLZYIK67NSXXZXCQV7XSJ/graph.json","events_json":"https://pith.science/api/pith-number/VSPQGJLZYIK67NSXXZXCQV7XSJ/events.json","paper":"https://pith.science/paper/VSPQGJLZ"},"agent_actions":{"view_html":"https://pith.science/pith/VSPQGJLZYIK67NSXXZXCQV7XSJ","download_json":"https://pith.science/pith/VSPQGJLZYIK67NSXXZXCQV7XSJ.json","view_paper":"https://pith.science/paper/VSPQGJLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28715&json=true","fetch_graph":"https://pith.science/api/pith-number/VSPQGJLZYIK67NSXXZXCQV7XSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VSPQGJLZYIK67NSXXZXCQV7XSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSPQGJLZYIK67NSXXZXCQV7XSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSPQGJLZYIK67NSXXZXCQV7XSJ/action/storage_attestation","attest_author":"https://pith.science/pith/VSPQGJLZYIK67NSXXZXCQV7XSJ/action/author_attestation","sign_citation":"https://pith.science/pith/VSPQGJLZYIK67NSXXZXCQV7XSJ/action/citation_signature","submit_replication":"https://pith.science/pith/VSPQGJLZYIK67NSXXZXCQV7XSJ/action/replication_record"}},"created_at":"2026-06-30T01:16:49.009308+00:00","updated_at":"2026-06-30T01:16:49.009308+00:00"}