{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A4TLHUGY7FEHUX6UM26KXLUFA7","short_pith_number":"pith:A4TLHUGY","schema_version":"1.0","canonical_sha256":"0726b3d0d8f9487a5fd466bcabae8507d37b3bf180341f524cb96343406f0c46","source":{"kind":"arxiv","id":"2507.16002","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Hindi NER in Low Context: A Comparative study of Transformer-based models with vs. without Retrieval Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Rohit Mishra, Sumit Singh, Uma Shanker Tiwary","submitted_at":"2025-07-21T18:41:58Z","abstract_excerpt":"One major challenge in natural language processing is named entity recognition (NER), which identifies and categorises named entities in textual input. In order to improve NER, this study investigates a Hindi NER technique that makes use of Hindi-specific pretrained encoders (MuRIL and XLM-R) and Generative Models ( Llama-2-7B-chat-hf (Llama2-7B), Llama-2-70B-chat-hf (Llama2-70B), Llama-3-70B-Instruct (Llama3-70B) and GPT3.5-turbo), and augments the data with retrieved data from external relevant contexts, notably from Wikipedia. We have fine-tuned MuRIL, XLM-R and Llama2-7B with and without R"},"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":"2507.16002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-21T18:41:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a668228177c014eaa15c27b3f1c9b06be80ec239adb71ccf7fad7ed29c1a2b9a","abstract_canon_sha256":"59c9ce928287ef02ebbcc13eb1087b0c858df8cd4372bad65bb328ba553bcee8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:00.866824Z","signature_b64":"wPOmHfCTpKC1nrB4kYOXItoYZw6q3E3XZPrDaRfjXE7skvhQbj5E6KfJaUVbZL8v38JCxqiUM4XhtgsOhKw0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0726b3d0d8f9487a5fd466bcabae8507d37b3bf180341f524cb96343406f0c46","last_reissued_at":"2026-07-05T11:41:00.866343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:00.866343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Hindi NER in Low Context: A Comparative study of Transformer-based models with vs. without Retrieval Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Rohit Mishra, Sumit Singh, Uma Shanker Tiwary","submitted_at":"2025-07-21T18:41:58Z","abstract_excerpt":"One major challenge in natural language processing is named entity recognition (NER), which identifies and categorises named entities in textual input. In order to improve NER, this study investigates a Hindi NER technique that makes use of Hindi-specific pretrained encoders (MuRIL and XLM-R) and Generative Models ( Llama-2-7B-chat-hf (Llama2-7B), Llama-2-70B-chat-hf (Llama2-70B), Llama-3-70B-Instruct (Llama3-70B) and GPT3.5-turbo), and augments the data with retrieved data from external relevant contexts, notably from Wikipedia. We have fine-tuned MuRIL, XLM-R and Llama2-7B with and without R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16002","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/2507.16002/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":"2507.16002","created_at":"2026-07-05T11:41:00.866398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16002v1","created_at":"2026-07-05T11:41:00.866398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16002","created_at":"2026-07-05T11:41:00.866398+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4TLHUGY7FEH","created_at":"2026-07-05T11:41:00.866398+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4TLHUGY7FEHUX6U","created_at":"2026-07-05T11:41:00.866398+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4TLHUGY","created_at":"2026-07-05T11:41:00.866398+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/A4TLHUGY7FEHUX6UM26KXLUFA7","json":"https://pith.science/pith/A4TLHUGY7FEHUX6UM26KXLUFA7.json","graph_json":"https://pith.science/api/pith-number/A4TLHUGY7FEHUX6UM26KXLUFA7/graph.json","events_json":"https://pith.science/api/pith-number/A4TLHUGY7FEHUX6UM26KXLUFA7/events.json","paper":"https://pith.science/paper/A4TLHUGY"},"agent_actions":{"view_html":"https://pith.science/pith/A4TLHUGY7FEHUX6UM26KXLUFA7","download_json":"https://pith.science/pith/A4TLHUGY7FEHUX6UM26KXLUFA7.json","view_paper":"https://pith.science/paper/A4TLHUGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16002&json=true","fetch_graph":"https://pith.science/api/pith-number/A4TLHUGY7FEHUX6UM26KXLUFA7/graph.json","fetch_events":"https://pith.science/api/pith-number/A4TLHUGY7FEHUX6UM26KXLUFA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4TLHUGY7FEHUX6UM26KXLUFA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4TLHUGY7FEHUX6UM26KXLUFA7/action/storage_attestation","attest_author":"https://pith.science/pith/A4TLHUGY7FEHUX6UM26KXLUFA7/action/author_attestation","sign_citation":"https://pith.science/pith/A4TLHUGY7FEHUX6UM26KXLUFA7/action/citation_signature","submit_replication":"https://pith.science/pith/A4TLHUGY7FEHUX6UM26KXLUFA7/action/replication_record"}},"created_at":"2026-07-05T11:41:00.866398+00:00","updated_at":"2026-07-05T11:41:00.866398+00:00"}