{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EXBJCCHRVJFDIJLTLMUYUUPE2B","short_pith_number":"pith:EXBJCCHR","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"},"canonical_sha256":"25c29108f1aa4a3425735b298a51e4d06f86275b4e07690f4018a9ac65c591c3","source":{"kind":"arxiv","id":"2605.28782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28782","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28782v1","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28782","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"EXBJCCHRVJFD","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"EXBJCCHRVJFDIJLT","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"EXBJCCHR","created_at":"2026-05-28T02:05:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EXBJCCHRVJFDIJLTLMUYUUPE2B","target":"record","payload":{"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"},"canonical_sha256":"25c29108f1aa4a3425735b298a51e4d06f86275b4e07690f4018a9ac65c591c3","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"},"source_kind":"arxiv","source_id":"2605.28782","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JiYh0H4XcdP8RUx1BdVlDVvFKwCaHdCJJSqWEJ/LY8nkR786nB5jLb0WxZFu3jiawKqpBBnqEj45R7SiCKE7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:23:02.725418Z"},"content_sha256":"88a2a25dd075a081f1ee3e9a41b96ff43588ed2de20de265509d0a43eb567a2e","schema_version":"1.0","event_id":"sha256:88a2a25dd075a081f1ee3e9a41b96ff43588ed2de20de265509d0a43eb567a2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EXBJCCHRVJFDIJLTLMUYUUPE2B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T02:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4zlcaknPwC+MmKRnxnT9aDA2v5wOhTGIKj5D3kyvvWHqKeEg4dBAR53Udd7rENGVynITRSD7PCxqs2997k+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:23:02.725806Z"},"content_sha256":"7503265cda4c2b586b1a07db0dcf6570da896ef0301993756f7cafbd3d8771e8","schema_version":"1.0","event_id":"sha256:7503265cda4c2b586b1a07db0dcf6570da896ef0301993756f7cafbd3d8771e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/bundle.json","state_url":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T06:23:02Z","links":{"resolver":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B","bundle":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/bundle.json","state":"https://pith.science/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXBJCCHRVJFDIJLTLMUYUUPE2B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EXBJCCHRVJFDIJLTLMUYUUPE2B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c1b02ff02dc268da51625c3f83e6ab150a52b7138f2842a5b4dc51d42cf1dfa5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T17:42:52Z","title_canon_sha256":"956928b8e5a5dc6eb30640a376398c94116e647472fe14514ddbab15675bdf11"},"schema_version":"1.0","source":{"id":"2605.28782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28782","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28782v1","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28782","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"EXBJCCHRVJFD","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"EXBJCCHRVJFDIJLT","created_at":"2026-05-28T02:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"EXBJCCHR","created_at":"2026-05-28T02:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:7503265cda4c2b586b1a07db0dcf6570da896ef0301993756f7cafbd3d8771e8","target":"graph","created_at":"2026-05-28T02:05:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.28782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bocheng Chen, Guangliang Liu, Jakin Tan, Mariah Al Giptiah Binte Yusoff, Xi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T17:42:52Z","title":"Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28782","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:88a2a25dd075a081f1ee3e9a41b96ff43588ed2de20de265509d0a43eb567a2e","target":"record","created_at":"2026-05-28T02:05:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c1b02ff02dc268da51625c3f83e6ab150a52b7138f2842a5b4dc51d42cf1dfa5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T17:42:52Z","title_canon_sha256":"956928b8e5a5dc6eb30640a376398c94116e647472fe14514ddbab15675bdf11"},"schema_version":"1.0","source":{"id":"2605.28782","kind":"arxiv","version":1}},"canonical_sha256":"25c29108f1aa4a3425735b298a51e4d06f86275b4e07690f4018a9ac65c591c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25c29108f1aa4a3425735b298a51e4d06f86275b4e07690f4018a9ac65c591c3","first_computed_at":"2026-05-28T02:05:03.497681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:05:03.497681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BSs1m4LRTC9AuO2hhI28E1YEh5ikvWqeN/R4vwZXSnoldLL3xKCuZuO16XHHKNYK8jN/AZHYWFsbpyVUoo7GCA==","signature_status":"signed_v1","signed_at":"2026-05-28T02:05:03.498107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88a2a25dd075a081f1ee3e9a41b96ff43588ed2de20de265509d0a43eb567a2e","sha256:7503265cda4c2b586b1a07db0dcf6570da896ef0301993756f7cafbd3d8771e8"],"state_sha256":"819128d9bd95e19cb420fbb8ae2456d745bb12a7bc167fc21ed210db6da14310"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1gHP0af1OPPMVkPVN0IPAozitlOd2cPT1TU5wM8QRRu20/KTCSkXouCFEKKjoPxDLv8DbZf30NVhVU/7UCSNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:23:02.728101Z","bundle_sha256":"51f50e1f71eef066cf8f9464b7ce61982cbf1144159ad3d1a63c2e4dc9782fa7"}}