{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZC3FCFZWMHAGSWQPSGZARBGBA3","short_pith_number":"pith:ZC3FCFZW","schema_version":"1.0","canonical_sha256":"c8b651173661c0695a0f91b20884c106e8d37ec791df20678d13aea7585dbbf6","source":{"kind":"arxiv","id":"2411.12240","version":2},"attestation_state":"computed","paper":{"title":"Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"D. J. Bora, S. Tamang","submitted_at":"2024-11-19T05:37:17Z","abstract_excerpt":"Large Language Models (LLMs) based on transformer architectures have revolutionized a variety of domains, with tokenization playing a pivotal role in their pre-processing and fine-tuning stages. In multilingual models, particularly those tailored for Indic languages, effective tokenization is crucial for optimizing performance. This paper presents a comprehensive evaluation of tokenizers used by 12 LLMs across all 22 official languages of India, with a focus on comparing the efficiency of their tokenization processes. We employed the Normalized Sequence Length (NSL) as a key metric in our anal"},"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":"2411.12240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T05:37:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"775e3b8f2ea8741ffd105702ed9dfc732823d9fc0e656244cc918de9e909cc97","abstract_canon_sha256":"8bee80f5fd5e898114dbe2e8f50009f773ed8fb397caed6fb088e374d5f4a5f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:44.744776Z","signature_b64":"qjQu0CDUvMA1UzOCsIruz5+87D6u0rZyzwyQGW5Yo9e/PK4NLd5IaJuNewBIZDmYP2IrcrNhkIEqVGFHWoScAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8b651173661c0695a0f91b20884c106e8d37ec791df20678d13aea7585dbbf6","last_reissued_at":"2026-07-05T09:40:44.744367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:44.744367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"D. J. Bora, S. Tamang","submitted_at":"2024-11-19T05:37:17Z","abstract_excerpt":"Large Language Models (LLMs) based on transformer architectures have revolutionized a variety of domains, with tokenization playing a pivotal role in their pre-processing and fine-tuning stages. In multilingual models, particularly those tailored for Indic languages, effective tokenization is crucial for optimizing performance. This paper presents a comprehensive evaluation of tokenizers used by 12 LLMs across all 22 official languages of India, with a focus on comparing the efficiency of their tokenization processes. We employed the Normalized Sequence Length (NSL) as a key metric in our anal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12240","kind":"arxiv","version":2},"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/2411.12240/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":"2411.12240","created_at":"2026-07-05T09:40:44.744424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12240v2","created_at":"2026-07-05T09:40:44.744424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12240","created_at":"2026-07-05T09:40:44.744424+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZC3FCFZWMHAG","created_at":"2026-07-05T09:40:44.744424+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZC3FCFZWMHAGSWQP","created_at":"2026-07-05T09:40:44.744424+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZC3FCFZW","created_at":"2026-07-05T09:40:44.744424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3","json":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3.json","graph_json":"https://pith.science/api/pith-number/ZC3FCFZWMHAGSWQPSGZARBGBA3/graph.json","events_json":"https://pith.science/api/pith-number/ZC3FCFZWMHAGSWQPSGZARBGBA3/events.json","paper":"https://pith.science/paper/ZC3FCFZW"},"agent_actions":{"view_html":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3","download_json":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3.json","view_paper":"https://pith.science/paper/ZC3FCFZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12240&json=true","fetch_graph":"https://pith.science/api/pith-number/ZC3FCFZWMHAGSWQPSGZARBGBA3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZC3FCFZWMHAGSWQPSGZARBGBA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3/action/storage_attestation","attest_author":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3/action/author_attestation","sign_citation":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3/action/citation_signature","submit_replication":"https://pith.science/pith/ZC3FCFZWMHAGSWQPSGZARBGBA3/action/replication_record"}},"created_at":"2026-07-05T09:40:44.744424+00:00","updated_at":"2026-07-05T09:40:44.744424+00:00"}