{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VQNB6G3CA52VHIAT3IGUCMCANA","short_pith_number":"pith:VQNB6G3C","schema_version":"1.0","canonical_sha256":"ac1a1f1b62077553a013da0d413040681b822fd4ffcfd721ac807ea6660840c8","source":{"kind":"arxiv","id":"2607.23344","version":1},"attestation_state":"computed","paper":{"title":"BERT-based Models vs. Large Language Models for Low-Resource Named Entity Recognition: A Comparative Study on Marathi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hariom Ingle, Ishwari Gondkar, Jidnyasa Harad, Raviraj Joshi, Ronit Ghode","submitted_at":"2026-07-25T19:40:58Z","abstract_excerpt":"Named Entity Recognition (NER) for low-resource languages such as Marathi remains a challenging task due to limited annotated resources and linguistic complexity. Although recent Large Language Models (LLMs) have demonstrated strong performance across a wide range of natural language processing tasks, their effectiveness for language-specific NER in low-resource settings remains uncertain. In this study, we fine-tune MahaBERT-v2 on different variants of the MahaNER dataset and systematically compare the performance of these models with an existing MahaNER baseline and prominent general-purpose"},"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":"2607.23344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T19:40:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b29eb4dc45026bfca7edc6ec56a4579c0ccd1328ffa8f291d80df3c2133bd339","abstract_canon_sha256":"28765663960747f8a79ffceb74bf0c533a64f52d967ce5076f99818d40be2645"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:48.550030Z","signature_b64":"RTc74M47yzAkXtVqtp+sokpyoOTfZsyZv6d9WuxAL0bQB9qUe5DbeWFaRkPd98YLv4vz6Ej81GqC4mj3hi7NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac1a1f1b62077553a013da0d413040681b822fd4ffcfd721ac807ea6660840c8","last_reissued_at":"2026-07-28T01:22:48.549246Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:48.549246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BERT-based Models vs. Large Language Models for Low-Resource Named Entity Recognition: A Comparative Study on Marathi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hariom Ingle, Ishwari Gondkar, Jidnyasa Harad, Raviraj Joshi, Ronit Ghode","submitted_at":"2026-07-25T19:40:58Z","abstract_excerpt":"Named Entity Recognition (NER) for low-resource languages such as Marathi remains a challenging task due to limited annotated resources and linguistic complexity. Although recent Large Language Models (LLMs) have demonstrated strong performance across a wide range of natural language processing tasks, their effectiveness for language-specific NER in low-resource settings remains uncertain. In this study, we fine-tune MahaBERT-v2 on different variants of the MahaNER dataset and systematically compare the performance of these models with an existing MahaNER baseline and prominent general-purpose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23344","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/2607.23344/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":"2607.23344","created_at":"2026-07-28T01:22:48.549658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23344v1","created_at":"2026-07-28T01:22:48.549658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23344","created_at":"2026-07-28T01:22:48.549658+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQNB6G3CA52V","created_at":"2026-07-28T01:22:48.549658+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQNB6G3CA52VHIAT","created_at":"2026-07-28T01:22:48.549658+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQNB6G3C","created_at":"2026-07-28T01:22:48.549658+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/VQNB6G3CA52VHIAT3IGUCMCANA","json":"https://pith.science/pith/VQNB6G3CA52VHIAT3IGUCMCANA.json","graph_json":"https://pith.science/api/pith-number/VQNB6G3CA52VHIAT3IGUCMCANA/graph.json","events_json":"https://pith.science/api/pith-number/VQNB6G3CA52VHIAT3IGUCMCANA/events.json","paper":"https://pith.science/paper/VQNB6G3C"},"agent_actions":{"view_html":"https://pith.science/pith/VQNB6G3CA52VHIAT3IGUCMCANA","download_json":"https://pith.science/pith/VQNB6G3CA52VHIAT3IGUCMCANA.json","view_paper":"https://pith.science/paper/VQNB6G3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23344&json=true","fetch_graph":"https://pith.science/api/pith-number/VQNB6G3CA52VHIAT3IGUCMCANA/graph.json","fetch_events":"https://pith.science/api/pith-number/VQNB6G3CA52VHIAT3IGUCMCANA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQNB6G3CA52VHIAT3IGUCMCANA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQNB6G3CA52VHIAT3IGUCMCANA/action/storage_attestation","attest_author":"https://pith.science/pith/VQNB6G3CA52VHIAT3IGUCMCANA/action/author_attestation","sign_citation":"https://pith.science/pith/VQNB6G3CA52VHIAT3IGUCMCANA/action/citation_signature","submit_replication":"https://pith.science/pith/VQNB6G3CA52VHIAT3IGUCMCANA/action/replication_record"}},"created_at":"2026-07-28T01:22:48.549658+00:00","updated_at":"2026-07-28T01:22:48.549658+00:00"}