{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BGDAUDDQC7EEZOFAC3QI7CLTR6","short_pith_number":"pith:BGDAUDDQ","schema_version":"1.0","canonical_sha256":"09860a0c7017c84cb8a016e08f89738f9914474c8fc9b2299a3c32ad2fbf7c45","source":{"kind":"arxiv","id":"2606.03284","version":1},"attestation_state":"computed","paper":{"title":"SEA-NLI: Natural Language Inference as a Lens into Southeast Asian Cultural Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Attapol T. Rutherford, Can Udomcharoenchaikit, Jian Gang Ngui, Peerat Limkonchotiwat, Peerawat Chomphooyod, Sarana Nutanong, Yosephine Susanto","submitted_at":"2026-06-02T07:49:50Z","abstract_excerpt":"Frontier LLMs perform well in Western contexts, but remain poorly tested on underrepresented cultures such as those in Southeast Asia (SEA). Existing NLI benchmarks are largely Western-centric, translation-derived, or monolingual, limiting their ability to measure culturally grounded reasoning. We introduce SEA-NLI, a native, culturally grounded NLI benchmark covering eight SEA countries in English and native regional languages, verified by native speakers. Across 17 encoder and decoder models, we observe a low performance from all models, especially for knowledge-intensive categories such as "},"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":"2606.03284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T07:49:50Z","cross_cats_sorted":[],"title_canon_sha256":"646ee3d2fc9da65629f75d513993f4185cd32b4553de85344cf10aa708cb0ab2","abstract_canon_sha256":"1c90107e42c28bac249589ce4a5c3385c90de4f4f3f534938a3572c130f402a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:38.220420Z","signature_b64":"6M0VzJOHhm34T7Zb33X35fIM9/fLU+uXIQY7iEajlC+B9/1GxNtY2NXD7IkabIa/F1d5R9YVHh/SP9NHyaebAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09860a0c7017c84cb8a016e08f89738f9914474c8fc9b2299a3c32ad2fbf7c45","last_reissued_at":"2026-06-03T01:05:38.219940Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:38.219940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEA-NLI: Natural Language Inference as a Lens into Southeast Asian Cultural Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Attapol T. Rutherford, Can Udomcharoenchaikit, Jian Gang Ngui, Peerat Limkonchotiwat, Peerawat Chomphooyod, Sarana Nutanong, Yosephine Susanto","submitted_at":"2026-06-02T07:49:50Z","abstract_excerpt":"Frontier LLMs perform well in Western contexts, but remain poorly tested on underrepresented cultures such as those in Southeast Asia (SEA). Existing NLI benchmarks are largely Western-centric, translation-derived, or monolingual, limiting their ability to measure culturally grounded reasoning. We introduce SEA-NLI, a native, culturally grounded NLI benchmark covering eight SEA countries in English and native regional languages, verified by native speakers. Across 17 encoder and decoder models, we observe a low performance from all models, especially for knowledge-intensive categories such as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03284","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/2606.03284/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":"2606.03284","created_at":"2026-06-03T01:05:38.220001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03284v1","created_at":"2026-06-03T01:05:38.220001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03284","created_at":"2026-06-03T01:05:38.220001+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGDAUDDQC7EE","created_at":"2026-06-03T01:05:38.220001+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGDAUDDQC7EEZOFA","created_at":"2026-06-03T01:05:38.220001+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGDAUDDQ","created_at":"2026-06-03T01:05:38.220001+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/BGDAUDDQC7EEZOFAC3QI7CLTR6","json":"https://pith.science/pith/BGDAUDDQC7EEZOFAC3QI7CLTR6.json","graph_json":"https://pith.science/api/pith-number/BGDAUDDQC7EEZOFAC3QI7CLTR6/graph.json","events_json":"https://pith.science/api/pith-number/BGDAUDDQC7EEZOFAC3QI7CLTR6/events.json","paper":"https://pith.science/paper/BGDAUDDQ"},"agent_actions":{"view_html":"https://pith.science/pith/BGDAUDDQC7EEZOFAC3QI7CLTR6","download_json":"https://pith.science/pith/BGDAUDDQC7EEZOFAC3QI7CLTR6.json","view_paper":"https://pith.science/paper/BGDAUDDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03284&json=true","fetch_graph":"https://pith.science/api/pith-number/BGDAUDDQC7EEZOFAC3QI7CLTR6/graph.json","fetch_events":"https://pith.science/api/pith-number/BGDAUDDQC7EEZOFAC3QI7CLTR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGDAUDDQC7EEZOFAC3QI7CLTR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGDAUDDQC7EEZOFAC3QI7CLTR6/action/storage_attestation","attest_author":"https://pith.science/pith/BGDAUDDQC7EEZOFAC3QI7CLTR6/action/author_attestation","sign_citation":"https://pith.science/pith/BGDAUDDQC7EEZOFAC3QI7CLTR6/action/citation_signature","submit_replication":"https://pith.science/pith/BGDAUDDQC7EEZOFAC3QI7CLTR6/action/replication_record"}},"created_at":"2026-06-03T01:05:38.220001+00:00","updated_at":"2026-06-03T01:05:38.220001+00:00"}