{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AKQAD7QQWZWDX7YGY3KCLIGR2X","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":"432b19cee52a3cc715af62555d3988dda7b0101dbe95cf436e00ecfd5b88daf9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T15:05:59Z","title_canon_sha256":"588f2e663c0bbb569dc2e9613e6d1e38bc7f9b6147a705ac37323e34c3a7ece7"},"schema_version":"1.0","source":{"id":"2412.13922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13922","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13922v1","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13922","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_12","alias_value":"AKQAD7QQWZWD","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_16","alias_value":"AKQAD7QQWZWDX7YG","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_8","alias_value":"AKQAD7QQ","created_at":"2026-07-05T09:51:10Z"}],"graph_snapshots":[{"event_id":"sha256:9914f13842cad1232c8f316353191638b43670f2f7056ea3d8707f64b16af6c4","target":"graph","created_at":"2026-07-05T09:51:10Z","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/2412.13922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are typically optimized for resource-rich languages like English, exacerbating the gap between high-resource and underrepresented languages. This work presents a detailed analysis of strategies for developing a model capable of following instructions in a low-resource language, specifically Basque, by focusing on three key stages: pre-training, instruction tuning, and alignment with human preferences. Our findings demonstrate that continual pre-training with a high-quality Basque corpus of around 600 million words improves natural language understanding (NLU) of th","authors_text":"Ander Corral, Ixak Sarasua, Xabier Saralegi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T15:05:59Z","title":"Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13922","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:a4d458ed9d4fadf7941fd1e4b88205b360913ffdea5ea741cf9a7f819dc1590a","target":"record","created_at":"2026-07-05T09:51:10Z","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":"432b19cee52a3cc715af62555d3988dda7b0101dbe95cf436e00ecfd5b88daf9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T15:05:59Z","title_canon_sha256":"588f2e663c0bbb569dc2e9613e6d1e38bc7f9b6147a705ac37323e34c3a7ece7"},"schema_version":"1.0","source":{"id":"2412.13922","kind":"arxiv","version":1}},"canonical_sha256":"02a001fe10b66c3bff06c6d425a0d1d5fa31a1c27b3254bac9ec84ef203e57e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02a001fe10b66c3bff06c6d425a0d1d5fa31a1c27b3254bac9ec84ef203e57e8","first_computed_at":"2026-07-05T09:51:10.883160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:10.883160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j3VKE3RgP+b+YCnpXJ/lCG4z1eczFADMBzNyf5lcDfd/+oi/Z4I+i6fUQOUZVfa/a32Tp1N1tkU3K3Dx3BBUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:10.883717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4d458ed9d4fadf7941fd1e4b88205b360913ffdea5ea741cf9a7f819dc1590a","sha256:9914f13842cad1232c8f316353191638b43670f2f7056ea3d8707f64b16af6c4"],"state_sha256":"45d7d7a742f08ae1c906cff23af72986c0efc76966754ed2aec9d8fddae5318e"}