{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EPIVBDSBS3PYG3ROH6VCCZZJC7","short_pith_number":"pith:EPIVBDSB","canonical_record":{"source":{"id":"2309.10661","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T14:42:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70a9b9497ba8cb50f1da29a4dae6e3b9c5ce73f9b5d1920613d1d1b9065e1fab","abstract_canon_sha256":"5f00699c7bbd6df3022a1f903d2a2e809e26fbea2fc2bcde9aeba9acd2de756d"},"schema_version":"1.0"},"canonical_sha256":"23d1508e4196df836e2e3faa21672917dabc62ec55075064ac907a023dd47aa2","source":{"kind":"arxiv","id":"2309.10661","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10661","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10661v2","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10661","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"pith_short_12","alias_value":"EPIVBDSBS3PY","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"pith_short_16","alias_value":"EPIVBDSBS3PYG3RO","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"pith_short_8","alias_value":"EPIVBDSB","created_at":"2026-07-05T06:52:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EPIVBDSBS3PYG3ROH6VCCZZJC7","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10661","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T14:42:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70a9b9497ba8cb50f1da29a4dae6e3b9c5ce73f9b5d1920613d1d1b9065e1fab","abstract_canon_sha256":"5f00699c7bbd6df3022a1f903d2a2e809e26fbea2fc2bcde9aeba9acd2de756d"},"schema_version":"1.0"},"canonical_sha256":"23d1508e4196df836e2e3faa21672917dabc62ec55075064ac907a023dd47aa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:26.841131Z","signature_b64":"zcAPeoVicD/B+DjknKnNQwEdP1mBFlp0U8yAsobHQqAZ/Cpy5RqcVLmY2dvoH9f9w0ZauoH24m64nUE0gwa5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d1508e4196df836e2e3faa21672917dabc62ec55075064ac907a023dd47aa2","last_reissued_at":"2026-07-05T06:52:26.840669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:26.840669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10661","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:52:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ElUy2nm4ZSVOCtyc7tLodfnZWWzOUsONVxqfwzHXCqTROwq/tvzln9bTAwTlMGPuXdyViWjHfGnRHRWSVox4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T05:10:16.134555Z"},"content_sha256":"332e3814134c422f44422bcb3eca99d5bb0be88e8cc83ceabbe7a7b7e88c7037","schema_version":"1.0","event_id":"sha256:332e3814134c422f44422bcb3eca99d5bb0be88e8cc83ceabbe7a7b7e88c7037"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EPIVBDSBS3PYG3ROH6VCCZZJC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Ayu Purwarianti, Bryan Wilie, David Moeljadi, Dea Adhista, Emmanuel Dave, Fajri Koto, Galih Pradipta Muridan, Genta Indra Winata, Hanung Wahyuning Linuwih, Holy Lovenia, Jhonson Lee, Nuur Shadieq, Pascale Fung, Salsabil Maulana Akbar, Samuel Cahyawijaya, Sarah Oktavianti, Tjeng Wawan Cenggoro","submitted_at":"2023-09-19T14:42:33Z","abstract_excerpt":"Democratizing access to natural language processing (NLP) technology is crucial, especially for underrepresented and extremely low-resource languages. Previous research has focused on developing labeled and unlabeled corpora for these languages through online scraping and document translation. While these methods have proven effective and cost-efficient, we have identified limitations in the resulting corpora, including a lack of lexical diversity and cultural relevance to local communities. To address this gap, we conduct a case study on Indonesian local languages. We compare the effectivenes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10661","kind":"arxiv","version":2},"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/2309.10661/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":"2026-07-05T06:52:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGeiInRekPCAszcT86nHCLugbXYeIPVbXv7jjCz/CwxRix3xEAGU0MGEL1ZzWfpVWF/nxIzz4C68AneTGVf2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T05:10:16.135057Z"},"content_sha256":"c5ddfb492f0618ccfdf04b03ccc743911f683af6e2615eefdc07721dac94390b","schema_version":"1.0","event_id":"sha256:c5ddfb492f0618ccfdf04b03ccc743911f683af6e2615eefdc07721dac94390b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPIVBDSBS3PYG3ROH6VCCZZJC7/bundle.json","state_url":"https://pith.science/pith/EPIVBDSBS3PYG3ROH6VCCZZJC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPIVBDSBS3PYG3ROH6VCCZZJC7/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":"2026-08-20T05:10:16Z","links":{"resolver":"https://pith.science/pith/EPIVBDSBS3PYG3ROH6VCCZZJC7","bundle":"https://pith.science/pith/EPIVBDSBS3PYG3ROH6VCCZZJC7/bundle.json","state":"https://pith.science/pith/EPIVBDSBS3PYG3ROH6VCCZZJC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPIVBDSBS3PYG3ROH6VCCZZJC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EPIVBDSBS3PYG3ROH6VCCZZJC7","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":"5f00699c7bbd6df3022a1f903d2a2e809e26fbea2fc2bcde9aeba9acd2de756d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T14:42:33Z","title_canon_sha256":"70a9b9497ba8cb50f1da29a4dae6e3b9c5ce73f9b5d1920613d1d1b9065e1fab"},"schema_version":"1.0","source":{"id":"2309.10661","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10661","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10661v2","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10661","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"pith_short_12","alias_value":"EPIVBDSBS3PY","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"pith_short_16","alias_value":"EPIVBDSBS3PYG3RO","created_at":"2026-07-05T06:52:26Z"},{"alias_kind":"pith_short_8","alias_value":"EPIVBDSB","created_at":"2026-07-05T06:52:26Z"}],"graph_snapshots":[{"event_id":"sha256:c5ddfb492f0618ccfdf04b03ccc743911f683af6e2615eefdc07721dac94390b","target":"graph","created_at":"2026-07-05T06:52:26Z","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/2309.10661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Democratizing access to natural language processing (NLP) technology is crucial, especially for underrepresented and extremely low-resource languages. Previous research has focused on developing labeled and unlabeled corpora for these languages through online scraping and document translation. While these methods have proven effective and cost-efficient, we have identified limitations in the resulting corpora, including a lack of lexical diversity and cultural relevance to local communities. To address this gap, we conduct a case study on Indonesian local languages. We compare the effectivenes","authors_text":"Alham Fikri Aji, Ayu Purwarianti, Bryan Wilie, David Moeljadi, Dea Adhista, Emmanuel Dave, Fajri Koto, Galih Pradipta Muridan, Genta Indra Winata, Hanung Wahyuning Linuwih, Holy Lovenia, Jhonson Lee, Nuur Shadieq, Pascale Fung, Salsabil Maulana Akbar, Samuel Cahyawijaya, Sarah Oktavianti, Tjeng Wawan Cenggoro","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T14:42:33Z","title":"NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10661","kind":"arxiv","version":2},"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":"sha256:332e3814134c422f44422bcb3eca99d5bb0be88e8cc83ceabbe7a7b7e88c7037","target":"record","created_at":"2026-07-05T06:52:26Z","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":"5f00699c7bbd6df3022a1f903d2a2e809e26fbea2fc2bcde9aeba9acd2de756d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T14:42:33Z","title_canon_sha256":"70a9b9497ba8cb50f1da29a4dae6e3b9c5ce73f9b5d1920613d1d1b9065e1fab"},"schema_version":"1.0","source":{"id":"2309.10661","kind":"arxiv","version":2}},"canonical_sha256":"23d1508e4196df836e2e3faa21672917dabc62ec55075064ac907a023dd47aa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23d1508e4196df836e2e3faa21672917dabc62ec55075064ac907a023dd47aa2","first_computed_at":"2026-07-05T06:52:26.840669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:26.840669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zcAPeoVicD/B+DjknKnNQwEdP1mBFlp0U8yAsobHQqAZ/Cpy5RqcVLmY2dvoH9f9w0ZauoH24m64nUE0gwa5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:26.841131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10661","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:332e3814134c422f44422bcb3eca99d5bb0be88e8cc83ceabbe7a7b7e88c7037","sha256:c5ddfb492f0618ccfdf04b03ccc743911f683af6e2615eefdc07721dac94390b"],"state_sha256":"c632d0f67fddbddb7a1a056ef543a73a49673eab6872a974313f29c677405562"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9U7oaLlStZ8zEiZP/XJOkpoTaDpr4NqfPi5mXSu5bvYIt+GjhLfTA8u9ziVSjm8dbjAD0aCtlsqS/kvqaZwUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T05:10:16.138850Z","bundle_sha256":"21fabf3e1995b6b36e411c7c76ebcc3a27d751c3073f014471f9df2ead701105"}}