{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:J2VUHOJF6ZA3JZAZK5HLKEFRDF","short_pith_number":"pith:J2VUHOJF","canonical_record":{"source":{"id":"2402.17302","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T08:24:32Z","cross_cats_sorted":[],"title_canon_sha256":"45d8322c9c68340c674adbbab2361de42907a9be4c472c15c566c50b24b06b2b","abstract_canon_sha256":"3cfbf0e70dcda6bce50b554d3ad9bf5868792f2d343cfca3bf2eca727a4d239c"},"schema_version":"1.0"},"canonical_sha256":"4eab43b925f641b4e419574eb510b1195f7e75aa66f51f2aed5f5c56cea76642","source":{"kind":"arxiv","id":"2402.17302","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17302","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17302v3","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17302","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_12","alias_value":"J2VUHOJF6ZA3","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_16","alias_value":"J2VUHOJF6ZA3JZAZ","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_8","alias_value":"J2VUHOJF","created_at":"2026-07-05T09:16:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:J2VUHOJF6ZA3JZAZK5HLKEFRDF","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17302","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T08:24:32Z","cross_cats_sorted":[],"title_canon_sha256":"45d8322c9c68340c674adbbab2361de42907a9be4c472c15c566c50b24b06b2b","abstract_canon_sha256":"3cfbf0e70dcda6bce50b554d3ad9bf5868792f2d343cfca3bf2eca727a4d239c"},"schema_version":"1.0"},"canonical_sha256":"4eab43b925f641b4e419574eb510b1195f7e75aa66f51f2aed5f5c56cea76642","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:13.143558Z","signature_b64":"LoUn9OQCnIidMM0twGsXwDUJVBWSSAg2Y2Ng7PU0oGJpFAfoIrhSWgWX8p2Mq7XBcu/iRRq2g0YHdgm5wG3VDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eab43b925f641b4e419574eb510b1195f7e75aa66f51f2aed5f5c56cea76642","last_reissued_at":"2026-07-05T09:16:13.143044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:13.143044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17302","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CQ8yL+5w4Qn47YVvLTTZT2SkZ3O0QtHjyBXOK9QAVc632jIMotxOWxCOwJhMcUE8gBUHAslccQODqgMBr3UgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:53:35.736404Z"},"content_sha256":"7425c82f1967bb7e53b3184f8f0b80cb004c3a8842a25cadf83e051147cbeaf0","schema_version":"1.0","event_id":"sha256:7425c82f1967bb7e53b3184f8f0b80cb004c3a8842a25cadf83e051147cbeaf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:J2VUHOJF6ZA3JZAZK5HLKEFRDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alice Oh, Dea Adhista, Faiz Ghifari Haznitrama, Rifki Afina Putri","submitted_at":"2024-02-27T08:24:32Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotator"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17302","kind":"arxiv","version":3},"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/2402.17302/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":"2026-07-05T09:16:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K7br1QB2easLp0YDnqP8F59Iam2atf0QnJI6UWHD3MYbQftk9r0RDgSpjzayThXbigvOuNU7E139PHvl3MshAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:53:35.736913Z"},"content_sha256":"9929844aa6844eba03f69f3209060ddf12de7ff4133263d6af024c8fedaa1cae","schema_version":"1.0","event_id":"sha256:9929844aa6844eba03f69f3209060ddf12de7ff4133263d6af024c8fedaa1cae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J2VUHOJF6ZA3JZAZK5HLKEFRDF/bundle.json","state_url":"https://pith.science/pith/J2VUHOJF6ZA3JZAZK5HLKEFRDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J2VUHOJF6ZA3JZAZK5HLKEFRDF/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":"2026-08-05T13:53:35Z","links":{"resolver":"https://pith.science/pith/J2VUHOJF6ZA3JZAZK5HLKEFRDF","bundle":"https://pith.science/pith/J2VUHOJF6ZA3JZAZK5HLKEFRDF/bundle.json","state":"https://pith.science/pith/J2VUHOJF6ZA3JZAZK5HLKEFRDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J2VUHOJF6ZA3JZAZK5HLKEFRDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J2VUHOJF6ZA3JZAZK5HLKEFRDF","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":"3cfbf0e70dcda6bce50b554d3ad9bf5868792f2d343cfca3bf2eca727a4d239c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T08:24:32Z","title_canon_sha256":"45d8322c9c68340c674adbbab2361de42907a9be4c472c15c566c50b24b06b2b"},"schema_version":"1.0","source":{"id":"2402.17302","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17302","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17302v3","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17302","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_12","alias_value":"J2VUHOJF6ZA3","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_16","alias_value":"J2VUHOJF6ZA3JZAZ","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_8","alias_value":"J2VUHOJF","created_at":"2026-07-05T09:16:13Z"}],"graph_snapshots":[{"event_id":"sha256:9929844aa6844eba03f69f3209060ddf12de7ff4133263d6af024c8fedaa1cae","target":"graph","created_at":"2026-07-05T09:16:13Z","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/2402.17302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly being used to generate synthetic data for training and evaluating models. However, it is unclear whether they can generate a good quality of question answering (QA) dataset that incorporates knowledge and cultural nuance embedded in a language, especially for low-resource languages. In this study, we investigate the effectiveness of using LLMs in generating culturally relevant commonsense QA datasets for Indonesian and Sundanese languages. To do so, we create datasets for these languages using various methods involving both LLMs and human annotator","authors_text":"Alice Oh, Dea Adhista, Faiz Ghifari Haznitrama, Rifki Afina Putri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T08:24:32Z","title":"Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17302","kind":"arxiv","version":3},"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":"sha256:7425c82f1967bb7e53b3184f8f0b80cb004c3a8842a25cadf83e051147cbeaf0","target":"record","created_at":"2026-07-05T09:16:13Z","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":"3cfbf0e70dcda6bce50b554d3ad9bf5868792f2d343cfca3bf2eca727a4d239c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T08:24:32Z","title_canon_sha256":"45d8322c9c68340c674adbbab2361de42907a9be4c472c15c566c50b24b06b2b"},"schema_version":"1.0","source":{"id":"2402.17302","kind":"arxiv","version":3}},"canonical_sha256":"4eab43b925f641b4e419574eb510b1195f7e75aa66f51f2aed5f5c56cea76642","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eab43b925f641b4e419574eb510b1195f7e75aa66f51f2aed5f5c56cea76642","first_computed_at":"2026-07-05T09:16:13.143044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:13.143044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LoUn9OQCnIidMM0twGsXwDUJVBWSSAg2Y2Ng7PU0oGJpFAfoIrhSWgWX8p2Mq7XBcu/iRRq2g0YHdgm5wG3VDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:13.143558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17302","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7425c82f1967bb7e53b3184f8f0b80cb004c3a8842a25cadf83e051147cbeaf0","sha256:9929844aa6844eba03f69f3209060ddf12de7ff4133263d6af024c8fedaa1cae"],"state_sha256":"1ce1d288dda5750e51579675c9a6011c0921409d28d5585e83e760c3d19e89a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ec+BZb13lzDEPn8iJC8MZpxuwjOfGUBO8swowAfCCOJTAW3wA56PdOOEPMMm52MRix49WWs011HAzIZO63cBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:53:35.740756Z","bundle_sha256":"edd172dd0d5e9a1c6a6370c23291a85b7ee3f526c5d5d7f6c14f3580c3f75d95"}}