{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YDDY37IIJT4OC5FAMRHR5VFN5P","short_pith_number":"pith:YDDY37II","schema_version":"1.0","canonical_sha256":"c0c78dfd084cf8e174a0644f1ed4adebed890603af771a7b63dc5c71d316c181","source":{"kind":"arxiv","id":"2505.19851","version":1},"attestation_state":"computed","paper":{"title":"Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Erik Cambria, Gulfarogh Azam, Mohammad Nadeem, Mohammad Sultan Alam, Mohd Sadique, Saif Ali, Shahab Saquib Sohail","submitted_at":"2025-05-26T11:35:51Z","abstract_excerpt":"Transliteration, the process of mapping text from one script to another, plays a crucial role in multilingual natural language processing, especially within linguistically diverse contexts such as India. Despite significant advancements through specialized models like IndicXlit, recent developments in large language models suggest a potential for general-purpose models to excel at this task without explicit task-specific training. The current work systematically evaluates the performance of prominent LLMs, including GPT-4o, GPT-4.5, GPT-4.1, Gemma-3-27B-it, and Mistral-Large against IndicXlit,"},"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":"2505.19851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T11:35:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a3662ecf3db2e0f714f9654298536f52569983d5695cce8f40bd67ae08d1bb59","abstract_canon_sha256":"7d725941052067b21f63b29e06dcff37d222e84d5d24b5bbb49e9c7347dcfb77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:48.936627Z","signature_b64":"v8B5cDwLJVf6RkTEQyiFC43UvSD7Y02FJ6livKkEilCBKHW6PS0b7sYLMv93VoRoEmF332zPr8SDXLHkPiziCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0c78dfd084cf8e174a0644f1ed4adebed890603af771a7b63dc5c71d316c181","last_reissued_at":"2026-07-05T11:09:48.936098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:48.936098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Erik Cambria, Gulfarogh Azam, Mohammad Nadeem, Mohammad Sultan Alam, Mohd Sadique, Saif Ali, Shahab Saquib Sohail","submitted_at":"2025-05-26T11:35:51Z","abstract_excerpt":"Transliteration, the process of mapping text from one script to another, plays a crucial role in multilingual natural language processing, especially within linguistically diverse contexts such as India. Despite significant advancements through specialized models like IndicXlit, recent developments in large language models suggest a potential for general-purpose models to excel at this task without explicit task-specific training. The current work systematically evaluates the performance of prominent LLMs, including GPT-4o, GPT-4.5, GPT-4.1, Gemma-3-27B-it, and Mistral-Large against IndicXlit,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19851","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/2505.19851/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":"2505.19851","created_at":"2026-07-05T11:09:48.936163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19851v1","created_at":"2026-07-05T11:09:48.936163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19851","created_at":"2026-07-05T11:09:48.936163+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDDY37IIJT4O","created_at":"2026-07-05T11:09:48.936163+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDDY37IIJT4OC5FA","created_at":"2026-07-05T11:09:48.936163+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDDY37II","created_at":"2026-07-05T11:09:48.936163+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/YDDY37IIJT4OC5FAMRHR5VFN5P","json":"https://pith.science/pith/YDDY37IIJT4OC5FAMRHR5VFN5P.json","graph_json":"https://pith.science/api/pith-number/YDDY37IIJT4OC5FAMRHR5VFN5P/graph.json","events_json":"https://pith.science/api/pith-number/YDDY37IIJT4OC5FAMRHR5VFN5P/events.json","paper":"https://pith.science/paper/YDDY37II"},"agent_actions":{"view_html":"https://pith.science/pith/YDDY37IIJT4OC5FAMRHR5VFN5P","download_json":"https://pith.science/pith/YDDY37IIJT4OC5FAMRHR5VFN5P.json","view_paper":"https://pith.science/paper/YDDY37II","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19851&json=true","fetch_graph":"https://pith.science/api/pith-number/YDDY37IIJT4OC5FAMRHR5VFN5P/graph.json","fetch_events":"https://pith.science/api/pith-number/YDDY37IIJT4OC5FAMRHR5VFN5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDDY37IIJT4OC5FAMRHR5VFN5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDDY37IIJT4OC5FAMRHR5VFN5P/action/storage_attestation","attest_author":"https://pith.science/pith/YDDY37IIJT4OC5FAMRHR5VFN5P/action/author_attestation","sign_citation":"https://pith.science/pith/YDDY37IIJT4OC5FAMRHR5VFN5P/action/citation_signature","submit_replication":"https://pith.science/pith/YDDY37IIJT4OC5FAMRHR5VFN5P/action/replication_record"}},"created_at":"2026-07-05T11:09:48.936163+00:00","updated_at":"2026-07-05T11:09:48.936163+00:00"}