{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EXBJCCHRVJFDIJLTLMUYUUPE2B","short_pith_number":"pith:EXBJCCHR","schema_version":"1.0","canonical_sha256":"25c29108f1aa4a3425735b298a51e4d06f86275b4e07690f4018a9ac65c591c3","source":{"kind":"arxiv","id":"2605.28782","version":1},"attestation_state":"computed","paper":{"title":"Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bocheng Chen, Guangliang Liu, Jakin Tan, Mariah Al Giptiah Binte Yusoff, Xi Chen","submitted_at":"2026-05-27T17:42:52Z","abstract_excerpt":"Discourse particles, such as \\textit{well} and \\textit{kind of}, are crucial components that enable LLMs to ``speak'' more like humans. They are used to convey emotions, intentions, and interpersonal meanings. However, existing studies have not yet built a comprehensive understanding of LLMs' capabilities in handling discourse particles. Moreover, the limited number of studies focuses primarily on high-resource languages such as English, with little attention paid to Southeast Asian languages. In this paper, we (1) propose \\textsc{MalayPrag}, a benchmark designed to systematically evaluate and"},"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":"2605.28782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T17:42:52Z","cross_cats_sorted":[],"title_canon_sha256":"956928b8e5a5dc6eb30640a376398c94116e647472fe14514ddbab15675bdf11","abstract_canon_sha256":"c1b02ff02dc268da51625c3f83e6ab150a52b7138f2842a5b4dc51d42cf1dfa5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:03.498107Z","signature_b64":"BSs1m4LRTC9AuO2hhI28E1YEh5ikvWqeN/R4vwZXSnoldLL3xKCuZuO16XHHKNYK8jN/AZHYWFsbpyVUoo7GCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25c29108f1aa4a3425735b298a51e4d06f86275b4e07690f4018a9ac65c591c3","last_reissued_at":"2026-05-28T02:05:03.497681Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:03.497681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bocheng Chen, Guangliang Liu, Jakin Tan, Mariah Al Giptiah Binte Yusoff, Xi Chen","submitted_at":"2026-05-27T17:42:52Z","abstract_excerpt":"Discourse particles, such as \\textit{well} and \\textit{kind of}, are crucial components that enable LLMs to ``speak'' more like humans. They are used to convey emotions, intentions, and interpersonal meanings. However, existing studies have not yet built a comprehensive understanding of LLMs' capabilities in handling discourse particles. Moreover, the limited number of studies focuses primarily on high-resource languages such as English, with little attention paid to Southeast Asian languages. In this paper, we (1) propose \\textsc{MalayPrag}, a benchmark designed to systematically evaluate and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28782","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/2605.28782/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":"2605.28782","created_at":"2026-05-28T02:05:03.497742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28782v1","created_at":"2026-05-28T02:05:03.497742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28782","created_at":"2026-05-28T02:05:03.497742+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXBJCCHRVJFD","created_at":"2026-05-28T02:05:03.497742+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXBJCCHRVJFDIJLT","created_at":"2026-05-28T02:05:03.497742+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXBJCCHR","created_at":"2026-05-28T02:05:03.497742+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/EXBJCCHRVJFDIJLTLMUYUUPE2B","json":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B.json","graph_json":"https://pith.science/api/pith-number/EXBJCCHRVJFDIJLTLMUYUUPE2B/graph.json","events_json":"https://pith.science/api/pith-number/EXBJCCHRVJFDIJLTLMUYUUPE2B/events.json","paper":"https://pith.science/paper/EXBJCCHR"},"agent_actions":{"view_html":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B","download_json":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B.json","view_paper":"https://pith.science/paper/EXBJCCHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28782&json=true","fetch_graph":"https://pith.science/api/pith-number/EXBJCCHRVJFDIJLTLMUYUUPE2B/graph.json","fetch_events":"https://pith.science/api/pith-number/EXBJCCHRVJFDIJLTLMUYUUPE2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/action/storage_attestation","attest_author":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/action/author_attestation","sign_citation":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/action/citation_signature","submit_replication":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/action/replication_record"}},"created_at":"2026-05-28T02:05:03.497742+00:00","updated_at":"2026-05-28T02:05:03.497742+00:00"}