{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WMTV52VH6FXNAXGRQQ2NE4DUZJ","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":"dce9f06f5c80eba6cdb8ce33ff66993f75b2dff4742e1777fc63585d95cd920f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T20:53:22Z","title_canon_sha256":"9b6cb49df7c02fbc6123fe7df59190078171d16e03f9204b03a81c447b31dc57"},"schema_version":"1.0","source":{"id":"2409.13897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13897","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13897v1","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13897","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"WMTV52VH6FXN","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"WMTV52VH6FXNAXGR","created_at":"2026-07-05T09:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"WMTV52VH","created_at":"2026-07-05T09:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:ff791872e4f70a342eb65284832a6ab2208f03a7d4b6784fc4ad71075552edd7","target":"graph","created_at":"2026-07-05T09:10:08Z","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/2409.13897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language processing (NLP) has witnessed a profound impact of large language models (LLMs) that excel in a multitude of tasks. However, the limitation of LLMs in multilingual settings, particularly in underrepresented languages, remains a significant hurdle. This thesis aims to bridge the gap in NLP research and development by focusing on underrepresented languages. A comprehensive evaluation of LLMs is conducted to assess their capabilities in these languages, revealing the challenges of multilingual and multicultural generalization. Addressing the multilingual generalization gap, this","authors_text":"Samuel Cahyawijaya","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T20:53:22Z","title":"LLM for Everyone: Representing the Underrepresented in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13897","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":"sha256:1315622bbca1813aad533a7ae90a34269be313aad79fa7c542b4890e8f240f08","target":"record","created_at":"2026-07-05T09:10:08Z","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":"dce9f06f5c80eba6cdb8ce33ff66993f75b2dff4742e1777fc63585d95cd920f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T20:53:22Z","title_canon_sha256":"9b6cb49df7c02fbc6123fe7df59190078171d16e03f9204b03a81c447b31dc57"},"schema_version":"1.0","source":{"id":"2409.13897","kind":"arxiv","version":1}},"canonical_sha256":"b3275eeaa7f16ed05cd18434d27074ca4aa21b6846489afd744aca8b4183ec6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3275eeaa7f16ed05cd18434d27074ca4aa21b6846489afd744aca8b4183ec6c","first_computed_at":"2026-07-05T09:10:08.388604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:08.388604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+RBHuRdu7Na2bt83/pBsWW3yTn7AoYWfKpYPJJEf6VU7r69rik4h7gUcQj4xYTYBidP7riDJYFo2aG4mV1BkBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:08.388941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1315622bbca1813aad533a7ae90a34269be313aad79fa7c542b4890e8f240f08","sha256:ff791872e4f70a342eb65284832a6ab2208f03a7d4b6784fc4ad71075552edd7"],"state_sha256":"1ee57aa47928a6ace0209c8aa767720fe020a8ac69358b9b7c75e2e673ee74ec"}