{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I77FVO55PMGCPKWWXSDZDZS6VV","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":"01c6d4cc114ed4e55d4699980927930a443ba1d857042b97c600da8388834058","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T23:18:06Z","title_canon_sha256":"0bb63c65251043cf5197fdceb628b1a3991d4951e1aa1cfd7c4bc92cea87e56b"},"schema_version":"1.0","source":{"id":"2412.13375","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13375","created_at":"2026-07-05T09:58:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13375v2","created_at":"2026-07-05T09:58:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13375","created_at":"2026-07-05T09:58:27Z"},{"alias_kind":"pith_short_12","alias_value":"I77FVO55PMGC","created_at":"2026-07-05T09:58:27Z"},{"alias_kind":"pith_short_16","alias_value":"I77FVO55PMGCPKWW","created_at":"2026-07-05T09:58:27Z"},{"alias_kind":"pith_short_8","alias_value":"I77FVO55","created_at":"2026-07-05T09:58:27Z"}],"graph_snapshots":[{"event_id":"sha256:e33b5ed16203550bc1d69f8ca634d0ccfd046c9e1ec0e421fadf2918c18ec17c","target":"graph","created_at":"2026-07-05T09:58:27Z","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/2412.13375/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have made great progress in classification and text generation tasks. However, they are mainly trained on English data and often struggle with low-resource languages. In this study, we explore adding a new language, i.e., Persian, to Llama (a model with a limited understanding of Persian) using parameter-efficient fine-tuning. We employ a multi-stage approach involving pretraining on monolingual Persian data, aligning representations through bilingual pretraining and instruction datasets, and instruction-tuning with task-specific datasets. We evaluate the model's p","authors_text":"Gholamreza Haffari, Pouya Sadeghi, Samin Mahdizadeh Sani, Thuy-Trang Vu, Yadollah Yaghoobzadeh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T23:18:06Z","title":"Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13375","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":"sha256:95e12b4595ddccfda88652fa3bf73eee2c41d050a36f2040b9b51530a18c1053","target":"record","created_at":"2026-07-05T09:58:27Z","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":"01c6d4cc114ed4e55d4699980927930a443ba1d857042b97c600da8388834058","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T23:18:06Z","title_canon_sha256":"0bb63c65251043cf5197fdceb628b1a3991d4951e1aa1cfd7c4bc92cea87e56b"},"schema_version":"1.0","source":{"id":"2412.13375","kind":"arxiv","version":2}},"canonical_sha256":"47fe5abbbd7b0c27aad6bc8791e65ead76861545ba70df00c8b3dc9a6993efa1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47fe5abbbd7b0c27aad6bc8791e65ead76861545ba70df00c8b3dc9a6993efa1","first_computed_at":"2026-07-05T09:58:27.019371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:27.019371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZgBE2quPhh0xr+8NyqWHpcwM233O+AB6HYhAzDKBsBSMGoSNKD/OvLMT3GaGod4udMZK9JOHVvFFYlQzuFphCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:27.019921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13375","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95e12b4595ddccfda88652fa3bf73eee2c41d050a36f2040b9b51530a18c1053","sha256:e33b5ed16203550bc1d69f8ca634d0ccfd046c9e1ec0e421fadf2918c18ec17c"],"state_sha256":"00248f1ba5ff660a33c44fdf8acbb6c78236267543fc6e7e2f6472a66495adc5"}