{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O6E2NRE63HWDV63RAZPHAOLB2P","short_pith_number":"pith:O6E2NRE6","schema_version":"1.0","canonical_sha256":"7789a6c49ed9ec3afb71065e703961d3df134a21a55c3ad41fe3c84c33584fa1","source":{"kind":"arxiv","id":"2312.01306","version":1},"attestation_state":"computed","paper":{"title":"On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anuja Patil, Dhanashree Lavekar, Harsh Chaudhari, Pranav Khairnar, Raviraj Joshi, Sachin Pande","submitted_at":"2023-12-03T06:53:53Z","abstract_excerpt":"Named Entity Recognition (NER) systems play a vital role in NLP applications such as machine translation, summarization, and question-answering. These systems identify named entities, which encompass real-world concepts like locations, persons, and organizations. Despite extensive research on NER systems for the English language, they have not received adequate attention in the context of low resource languages. In this work, we focus on NER for low-resource language and present our case study in the context of the Indian language Marathi. The advancement of NLP research revolves around the ut"},"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":"2312.01306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-03T06:53:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c40d7380127aaa0d9a1149906c05616cf71f2e3aa730f1f7f1f234f8b5dc750","abstract_canon_sha256":"318e575ec998719cfdc385d2e210b242e983ea59ebd2480f8b0f73b8db0ff7ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:33.063676Z","signature_b64":"Fj5If/ystAekbfZ3J3CJ9hLu76RgTAVvXn2CANCo1wUnqQ2yGx2uRtqMX0XHL3DcV65hG7JYIcAUBxrFZ6N3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7789a6c49ed9ec3afb71065e703961d3df134a21a55c3ad41fe3c84c33584fa1","last_reissued_at":"2026-07-05T07:19:33.063204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:33.063204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anuja Patil, Dhanashree Lavekar, Harsh Chaudhari, Pranav Khairnar, Raviraj Joshi, Sachin Pande","submitted_at":"2023-12-03T06:53:53Z","abstract_excerpt":"Named Entity Recognition (NER) systems play a vital role in NLP applications such as machine translation, summarization, and question-answering. These systems identify named entities, which encompass real-world concepts like locations, persons, and organizations. Despite extensive research on NER systems for the English language, they have not received adequate attention in the context of low resource languages. In this work, we focus on NER for low-resource language and present our case study in the context of the Indian language Marathi. The advancement of NLP research revolves around the ut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01306","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/2312.01306/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":"2312.01306","created_at":"2026-07-05T07:19:33.063251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01306v1","created_at":"2026-07-05T07:19:33.063251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01306","created_at":"2026-07-05T07:19:33.063251+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6E2NRE63HWD","created_at":"2026-07-05T07:19:33.063251+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6E2NRE63HWDV63R","created_at":"2026-07-05T07:19:33.063251+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6E2NRE6","created_at":"2026-07-05T07:19:33.063251+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/O6E2NRE63HWDV63RAZPHAOLB2P","json":"https://pith.science/pith/O6E2NRE63HWDV63RAZPHAOLB2P.json","graph_json":"https://pith.science/api/pith-number/O6E2NRE63HWDV63RAZPHAOLB2P/graph.json","events_json":"https://pith.science/api/pith-number/O6E2NRE63HWDV63RAZPHAOLB2P/events.json","paper":"https://pith.science/paper/O6E2NRE6"},"agent_actions":{"view_html":"https://pith.science/pith/O6E2NRE63HWDV63RAZPHAOLB2P","download_json":"https://pith.science/pith/O6E2NRE63HWDV63RAZPHAOLB2P.json","view_paper":"https://pith.science/paper/O6E2NRE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01306&json=true","fetch_graph":"https://pith.science/api/pith-number/O6E2NRE63HWDV63RAZPHAOLB2P/graph.json","fetch_events":"https://pith.science/api/pith-number/O6E2NRE63HWDV63RAZPHAOLB2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6E2NRE63HWDV63RAZPHAOLB2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6E2NRE63HWDV63RAZPHAOLB2P/action/storage_attestation","attest_author":"https://pith.science/pith/O6E2NRE63HWDV63RAZPHAOLB2P/action/author_attestation","sign_citation":"https://pith.science/pith/O6E2NRE63HWDV63RAZPHAOLB2P/action/citation_signature","submit_replication":"https://pith.science/pith/O6E2NRE63HWDV63RAZPHAOLB2P/action/replication_record"}},"created_at":"2026-07-05T07:19:33.063251+00:00","updated_at":"2026-07-05T07:19:33.063251+00:00"}