{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YTMYTTIY6DF7I7GD5MG5KCPGUO","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":"ec60cefba0f6de8c5b9cebeef954ecd48f46a7c30255dd05003ad1dcfb8487b1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T17:41:08Z","title_canon_sha256":"5bb845b1cd593b74f139864246d9deebdd60a475a17eb0ccfae940b1f718f57b"},"schema_version":"1.0","source":{"id":"2411.14343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14343","created_at":"2026-07-05T09:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14343v1","created_at":"2026-07-05T09:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14343","created_at":"2026-07-05T09:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"YTMYTTIY6DF7","created_at":"2026-07-05T09:38:45Z"},{"alias_kind":"pith_short_16","alias_value":"YTMYTTIY6DF7I7GD","created_at":"2026-07-05T09:38:45Z"},{"alias_kind":"pith_short_8","alias_value":"YTMYTTIY","created_at":"2026-07-05T09:38:45Z"}],"graph_snapshots":[{"event_id":"sha256:1efab86f8afe61773a7e4dca49aec9c128584af9723877046cded435fc7c3070","target":"graph","created_at":"2026-07-05T09:38:45Z","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/2411.14343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) under-perform on low-resource languages due to limited training data. We present a method to efficiently collect text data for low-resource languages from the entire Common Crawl corpus. Our approach, UnifiedCrawl, filters and extracts common crawl using minimal compute resources, yielding mono-lingual datasets much larger than previously available sources. We demonstrate that leveraging this data to fine-tuning multilingual LLMs via efficient adapter methods (QLoRA) significantly boosts performance on the low-resource language, while minimizing VRAM usage. Our exp","authors_text":"(2) Independent Researcher), Akhil Kedia (2), Bethel Melesse Tessema (1), Tae-Sun Chung (1) ((1) Ajou University","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T17:41:08Z","title":"UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14343","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":"sha256:194621cc8b7b4c4bcbe41b291fc0ad524c60517f97210787ba938f2a1d5e0f75","target":"record","created_at":"2026-07-05T09:38:45Z","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":"ec60cefba0f6de8c5b9cebeef954ecd48f46a7c30255dd05003ad1dcfb8487b1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T17:41:08Z","title_canon_sha256":"5bb845b1cd593b74f139864246d9deebdd60a475a17eb0ccfae940b1f718f57b"},"schema_version":"1.0","source":{"id":"2411.14343","kind":"arxiv","version":1}},"canonical_sha256":"c4d989cd18f0cbf47cc3eb0dd509e6a3954d162c417e9c3e53305d811a1099e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4d989cd18f0cbf47cc3eb0dd509e6a3954d162c417e9c3e53305d811a1099e8","first_computed_at":"2026-07-05T09:38:45.492224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:45.492224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MJyVjX7yxN3GoZJ/7XJPkRXY+PGjZ0sFnkjThj0a3jV1jCfkC7oXXIdiGzR4UBvUvxo6DIWp0KRcahtpnP4GBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:45.492741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:194621cc8b7b4c4bcbe41b291fc0ad524c60517f97210787ba938f2a1d5e0f75","sha256:1efab86f8afe61773a7e4dca49aec9c128584af9723877046cded435fc7c3070"],"state_sha256":"bf0f60e38542259036b5e54e8d17b53808513a81c8a1a6ba67d4ac0656390d79"}