{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FZV5UWAE2CAM7TU4HLEPZ6CMQQ","short_pith_number":"pith:FZV5UWAE","schema_version":"1.0","canonical_sha256":"2e6bda5804d080cfce9c3ac8fcf84c842f1b4df0dd3ca2c9ea2d6e9b6f0b8096","source":{"kind":"arxiv","id":"2311.05845","version":1},"attestation_state":"computed","paper":{"title":"Tamil-Llama: A New Tamil Language Model Based on Llama 2","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhinand Balachandran","submitted_at":"2023-11-10T03:02:39Z","abstract_excerpt":"Language modeling has witnessed remarkable advancements in recent years, with Large Language Models (LLMs) like ChatGPT setting unparalleled benchmarks in human-like text generation. However, a prevailing limitation is the underrepresentation of languages like Tamil in these cutting-edge models, leading to suboptimal performance in diverse linguistic contexts. This paper addresses this lacuna, enhancing the open-source LLaMA model with an addition of 16,000 Tamil tokens, aiming to achieve superior text generation and comprehension in the Tamil language. We strategically employ the LoRA methodo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.05845","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T03:02:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0abbb61b4a714979a92b260b80d5e66df605b533a8f98ea48a914567a188461e","abstract_canon_sha256":"a175ab982c106f2c9c09e1111eff65ca86c7cf56d21c7dbbab5a39c0944f0dc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:23.836540Z","signature_b64":"vA7S9nApbmauWHXF4pliwcbnjFr9oFNNwJZcenwfDzkrM1ifpF9oNgXjhBDsqITjWThzwGjUz5WFO/xktDOWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6bda5804d080cfce9c3ac8fcf84c842f1b4df0dd3ca2c9ea2d6e9b6f0b8096","last_reissued_at":"2026-07-05T07:11:23.836120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:23.836120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tamil-Llama: A New Tamil Language Model Based on Llama 2","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhinand Balachandran","submitted_at":"2023-11-10T03:02:39Z","abstract_excerpt":"Language modeling has witnessed remarkable advancements in recent years, with Large Language Models (LLMs) like ChatGPT setting unparalleled benchmarks in human-like text generation. However, a prevailing limitation is the underrepresentation of languages like Tamil in these cutting-edge models, leading to suboptimal performance in diverse linguistic contexts. This paper addresses this lacuna, enhancing the open-source LLaMA model with an addition of 16,000 Tamil tokens, aiming to achieve superior text generation and comprehension in the Tamil language. We strategically employ the LoRA methodo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05845","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.05845/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.05845","created_at":"2026-07-05T07:11:23.836176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05845v1","created_at":"2026-07-05T07:11:23.836176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05845","created_at":"2026-07-05T07:11:23.836176+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZV5UWAE2CAM","created_at":"2026-07-05T07:11:23.836176+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZV5UWAE2CAM7TU4","created_at":"2026-07-05T07:11:23.836176+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZV5UWAE","created_at":"2026-07-05T07:11:23.836176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30790","citing_title":"Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2602.14517","citing_title":"Large Language Models for Math Education in Low-Resource Languages: A Study in Sinhala and Tamil","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ","json":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ.json","graph_json":"https://pith.science/api/pith-number/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/graph.json","events_json":"https://pith.science/api/pith-number/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/events.json","paper":"https://pith.science/paper/FZV5UWAE"},"agent_actions":{"view_html":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ","download_json":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ.json","view_paper":"https://pith.science/paper/FZV5UWAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05845&json=true","fetch_graph":"https://pith.science/api/pith-number/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/action/storage_attestation","attest_author":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/action/author_attestation","sign_citation":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/action/citation_signature","submit_replication":"https://pith.science/pith/FZV5UWAE2CAM7TU4HLEPZ6CMQQ/action/replication_record"}},"created_at":"2026-07-05T07:11:23.836176+00:00","updated_at":"2026-07-05T07:11:23.836176+00:00"}