{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TX7TB5GPHVAOZPW6LJXIZ6FVZO","short_pith_number":"pith:TX7TB5GP","schema_version":"1.0","canonical_sha256":"9dff30f4cf3d40ecbede5a6e8cf8b5cba2cdcd3c1350efc3ec9147b50df71bc4","source":{"kind":"arxiv","id":"2205.14728","version":2},"attestation_state":"computed","paper":{"title":"L3Cube-MahaNLP: Marathi Natural Language Processing Datasets, Models, and Library","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Raviraj Joshi","submitted_at":"2022-05-29T17:51:00Z","abstract_excerpt":"Despite being the third most popular language in India, the Marathi language lacks useful NLP resources. Moreover, popular NLP libraries do not have support for the Marathi language. With L3Cube-MahaNLP, we aim to build resources and a library for Marathi natural language processing. We present datasets and transformer models for supervised tasks like sentiment analysis, named entity recognition, and hate speech detection. We have also published a monolingual Marathi corpus for unsupervised language modeling tasks. Overall we present MahaCorpus, MahaSent, MahaNER, and MahaHate datasets and the"},"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":"2205.14728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-29T17:51:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"acf079d0ecb2b5e46147873274d4c383652f12a8514343435fc7d5f43aa19f59","abstract_canon_sha256":"c42f33bb95394d62cb66ee70d455104846c12310f649a454e67c70a7844da053"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:01.189956Z","signature_b64":"9Rgp4t+zMgxqMrcd7ehmAI3pew3vO7U9quax9Hd5p6i25jX9TN6UilMHIqdmsLlOweIN5VVgw5MlPcUNqtJ6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dff30f4cf3d40ecbede5a6e8cf8b5cba2cdcd3c1350efc3ec9147b50df71bc4","last_reissued_at":"2026-07-05T04:28:01.189506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:01.189506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L3Cube-MahaNLP: Marathi Natural Language Processing Datasets, Models, and Library","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Raviraj Joshi","submitted_at":"2022-05-29T17:51:00Z","abstract_excerpt":"Despite being the third most popular language in India, the Marathi language lacks useful NLP resources. Moreover, popular NLP libraries do not have support for the Marathi language. With L3Cube-MahaNLP, we aim to build resources and a library for Marathi natural language processing. We present datasets and transformer models for supervised tasks like sentiment analysis, named entity recognition, and hate speech detection. We have also published a monolingual Marathi corpus for unsupervised language modeling tasks. Overall we present MahaCorpus, MahaSent, MahaNER, and MahaHate datasets and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14728","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/2205.14728/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":"2205.14728","created_at":"2026-07-05T04:28:01.189563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14728v2","created_at":"2026-07-05T04:28:01.189563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14728","created_at":"2026-07-05T04:28:01.189563+00:00"},{"alias_kind":"pith_short_12","alias_value":"TX7TB5GPHVAO","created_at":"2026-07-05T04:28:01.189563+00:00"},{"alias_kind":"pith_short_16","alias_value":"TX7TB5GPHVAOZPW6","created_at":"2026-07-05T04:28:01.189563+00:00"},{"alias_kind":"pith_short_8","alias_value":"TX7TB5GP","created_at":"2026-07-05T04:28:01.189563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24825","citing_title":"L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22841","citing_title":"IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28796","citing_title":"Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO","json":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO.json","graph_json":"https://pith.science/api/pith-number/TX7TB5GPHVAOZPW6LJXIZ6FVZO/graph.json","events_json":"https://pith.science/api/pith-number/TX7TB5GPHVAOZPW6LJXIZ6FVZO/events.json","paper":"https://pith.science/paper/TX7TB5GP"},"agent_actions":{"view_html":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO","download_json":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO.json","view_paper":"https://pith.science/paper/TX7TB5GP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14728&json=true","fetch_graph":"https://pith.science/api/pith-number/TX7TB5GPHVAOZPW6LJXIZ6FVZO/graph.json","fetch_events":"https://pith.science/api/pith-number/TX7TB5GPHVAOZPW6LJXIZ6FVZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO/action/storage_attestation","attest_author":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO/action/author_attestation","sign_citation":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO/action/citation_signature","submit_replication":"https://pith.science/pith/TX7TB5GPHVAOZPW6LJXIZ6FVZO/action/replication_record"}},"created_at":"2026-07-05T04:28:01.189563+00:00","updated_at":"2026-07-05T04:28:01.189563+00:00"}