{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BIJ2SRRUDJM4LIBNNYOYFNUOQI","short_pith_number":"pith:BIJ2SRRU","schema_version":"1.0","canonical_sha256":"0a13a946341a59c5a02d6e1d82b68e822c46ac4a2211b98533785c97cb398752","source":{"kind":"arxiv","id":"2401.00170","version":1},"attestation_state":"computed","paper":{"title":"L3Cube-MahaSocialNER: A Social Media based Marathi NER Dataset and BERT models","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","submitted_at":"2023-12-30T08:30:24Z","abstract_excerpt":"This work introduces the L3Cube-MahaSocialNER dataset, the first and largest social media dataset specifically designed for Named Entity Recognition (NER) in the Marathi language. The dataset comprises 18,000 manually labeled sentences covering eight entity classes, addressing challenges posed by social media data, including non-standard language and informal idioms. Deep learning models, including CNN, LSTM, BiLSTM, and Transformer models, are evaluated on the individual dataset with IOB and non-IOB notations. The results demonstrate the effectiveness of these models in accurately recognizing"},"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":"2401.00170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-30T08:30:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a40ddf3f997f45bcf4fb039e28f0040acd0c8beba06b77901f48dcf727ed3aa8","abstract_canon_sha256":"3579575665127fe750668423790ec78fd5d2de32a8ee43df8fbeb33517ed8d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:58.885728Z","signature_b64":"0kWeTWiKiseyWTno32j+UuwEHT8OcJRU44sk5pS+8wU/ajdVphS+jPBq+k5E3whYv/e1KM026csaRp4xZ/o2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a13a946341a59c5a02d6e1d82b68e822c46ac4a2211b98533785c97cb398752","last_reissued_at":"2026-07-05T07:44:58.885281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:58.885281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L3Cube-MahaSocialNER: A Social Media based Marathi NER Dataset and BERT models","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","submitted_at":"2023-12-30T08:30:24Z","abstract_excerpt":"This work introduces the L3Cube-MahaSocialNER dataset, the first and largest social media dataset specifically designed for Named Entity Recognition (NER) in the Marathi language. The dataset comprises 18,000 manually labeled sentences covering eight entity classes, addressing challenges posed by social media data, including non-standard language and informal idioms. Deep learning models, including CNN, LSTM, BiLSTM, and Transformer models, are evaluated on the individual dataset with IOB and non-IOB notations. The results demonstrate the effectiveness of these models in accurately recognizing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00170","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/2401.00170/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":"2401.00170","created_at":"2026-07-05T07:44:58.885345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00170v1","created_at":"2026-07-05T07:44:58.885345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00170","created_at":"2026-07-05T07:44:58.885345+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIJ2SRRUDJM4","created_at":"2026-07-05T07:44:58.885345+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIJ2SRRUDJM4LIBN","created_at":"2026-07-05T07:44:58.885345+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIJ2SRRU","created_at":"2026-07-05T07:44:58.885345+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/BIJ2SRRUDJM4LIBNNYOYFNUOQI","json":"https://pith.science/pith/BIJ2SRRUDJM4LIBNNYOYFNUOQI.json","graph_json":"https://pith.science/api/pith-number/BIJ2SRRUDJM4LIBNNYOYFNUOQI/graph.json","events_json":"https://pith.science/api/pith-number/BIJ2SRRUDJM4LIBNNYOYFNUOQI/events.json","paper":"https://pith.science/paper/BIJ2SRRU"},"agent_actions":{"view_html":"https://pith.science/pith/BIJ2SRRUDJM4LIBNNYOYFNUOQI","download_json":"https://pith.science/pith/BIJ2SRRUDJM4LIBNNYOYFNUOQI.json","view_paper":"https://pith.science/paper/BIJ2SRRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00170&json=true","fetch_graph":"https://pith.science/api/pith-number/BIJ2SRRUDJM4LIBNNYOYFNUOQI/graph.json","fetch_events":"https://pith.science/api/pith-number/BIJ2SRRUDJM4LIBNNYOYFNUOQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIJ2SRRUDJM4LIBNNYOYFNUOQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIJ2SRRUDJM4LIBNNYOYFNUOQI/action/storage_attestation","attest_author":"https://pith.science/pith/BIJ2SRRUDJM4LIBNNYOYFNUOQI/action/author_attestation","sign_citation":"https://pith.science/pith/BIJ2SRRUDJM4LIBNNYOYFNUOQI/action/citation_signature","submit_replication":"https://pith.science/pith/BIJ2SRRUDJM4LIBNNYOYFNUOQI/action/replication_record"}},"created_at":"2026-07-05T07:44:58.885345+00:00","updated_at":"2026-07-05T07:44:58.885345+00:00"}