{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6KQJR5TYD244WBIHDPW4RZJBAZ","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":"8c53534e7bc4e6fc91d03652944aedaf47e809fae2c94686e977479463913a18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T08:57:39Z","title_canon_sha256":"a852654eeafded45e773190ad5934c9814010c612ee93ddbdbc791ea8e62e039"},"schema_version":"1.0","source":{"id":"2401.13303","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13303","created_at":"2026-07-05T08:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13303v2","created_at":"2026-07-05T08:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13303","created_at":"2026-07-05T08:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"6KQJR5TYD244","created_at":"2026-07-05T08:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"6KQJR5TYD244WBIH","created_at":"2026-07-05T08:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"6KQJR5TY","created_at":"2026-07-05T08:03:48Z"}],"graph_snapshots":[{"event_id":"sha256:13d46c8d3c2c08f9637208655209226f0bea38b68f1a24bafdf36180cce75811","target":"graph","created_at":"2026-07-05T08:03:48Z","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/2401.13303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have advanced the state of the art in natural language processing. However, their predominant design for English or a limited set of languages creates a substantial gap in their effectiveness for low-resource languages. To bridge this gap, we introduce MaLA-500, a novel large language model designed to cover an extensive range of 534 languages. To train MaLA-500, we employ vocabulary extension and continued pretraining on LLaMA 2 with Glot500-c. Our intrinsic evaluation demonstrates that MaLA-500 is better at predicting the given texts of low-resource languages tha","authors_text":"Andr\\'e F. T. Martins, Hinrich Sch\\\"utze, J\\\"org Tiedemann, Peiqin Lin, Shaoxiong Ji","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T08:57:39Z","title":"MaLA-500: Massive Language Adaptation of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13303","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":"sha256:7a6023321ab82f12e20eca8d3911ffc38947f3d40dcd395efaf0d2771b2420b6","target":"record","created_at":"2026-07-05T08:03:48Z","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":"8c53534e7bc4e6fc91d03652944aedaf47e809fae2c94686e977479463913a18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T08:57:39Z","title_canon_sha256":"a852654eeafded45e773190ad5934c9814010c612ee93ddbdbc791ea8e62e039"},"schema_version":"1.0","source":{"id":"2401.13303","kind":"arxiv","version":2}},"canonical_sha256":"f2a098f6781eb9cb05071bedc8e521067cf5dc90ece3c359750bf04bd332d677","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2a098f6781eb9cb05071bedc8e521067cf5dc90ece3c359750bf04bd332d677","first_computed_at":"2026-07-05T08:03:48.397739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:48.397739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MQwP532jOR60U8YG47ejBzxvea94qpFLyop+lnPePE/NPDuAUZ8cboKsDqkHR9zNYcREcrXhIJLWjM31r0w7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:48.398158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13303","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a6023321ab82f12e20eca8d3911ffc38947f3d40dcd395efaf0d2771b2420b6","sha256:13d46c8d3c2c08f9637208655209226f0bea38b68f1a24bafdf36180cce75811"],"state_sha256":"7a29979a73760d4d1241b9b575676b5f202a0ff0730d06e5eebae491580e1f3d"}