{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:56SRTPTYZDZ55IQTXFCHEZ5AL5","short_pith_number":"pith:56SRTPTY","schema_version":"1.0","canonical_sha256":"efa519be78c8f3dea213b9447267a05f421b1c3e6e620cc2b64c756091cedebe","source":{"kind":"arxiv","id":"2204.08669","version":1},"attestation_state":"computed","paper":{"title":"Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: 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":"Abhishek Velankar, Hrushikesh Patil, Raviraj Joshi","submitted_at":"2022-04-19T05:07:58Z","abstract_excerpt":"Transformers are the most eminent architectures used for a vast range of Natural Language Processing tasks. These models are pre-trained over a large text corpus and are meant to serve state-of-the-art results over tasks like text classification. In this work, we conduct a comparative study between monolingual and multilingual BERT models. We focus on the Marathi language and evaluate the models on the datasets for hate speech detection, sentiment analysis and simple text classification in Marathi. We use standard multilingual models such as mBERT, indicBERT and xlm-RoBERTa and compare with Ma"},"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":"2204.08669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-19T05:07:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"db0199688c637473f69c8de04563d2f41491640f98796bf985c6f03b7e609134","abstract_canon_sha256":"84a094297ca3b8f24fabba2f3a484822b78535f7ddb202059ee84808ff07e506"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:23.159214Z","signature_b64":"Jdwt0QzOb9rA+8pjowKtbwFCackuNeDcE2T225jhxGKGVpnRfQCcsUP2o2O9zbPjr3tSPyg9VXujrRRSHgMGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efa519be78c8f3dea213b9447267a05f421b1c3e6e620cc2b64c756091cedebe","last_reissued_at":"2026-07-05T05:15:23.158765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:23.158765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: 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":"Abhishek Velankar, Hrushikesh Patil, Raviraj Joshi","submitted_at":"2022-04-19T05:07:58Z","abstract_excerpt":"Transformers are the most eminent architectures used for a vast range of Natural Language Processing tasks. These models are pre-trained over a large text corpus and are meant to serve state-of-the-art results over tasks like text classification. In this work, we conduct a comparative study between monolingual and multilingual BERT models. We focus on the Marathi language and evaluate the models on the datasets for hate speech detection, sentiment analysis and simple text classification in Marathi. We use standard multilingual models such as mBERT, indicBERT and xlm-RoBERTa and compare with Ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08669","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/2204.08669/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":"2204.08669","created_at":"2026-07-05T05:15:23.158817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08669v1","created_at":"2026-07-05T05:15:23.158817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08669","created_at":"2026-07-05T05:15:23.158817+00:00"},{"alias_kind":"pith_short_12","alias_value":"56SRTPTYZDZ5","created_at":"2026-07-05T05:15:23.158817+00:00"},{"alias_kind":"pith_short_16","alias_value":"56SRTPTYZDZ55IQT","created_at":"2026-07-05T05:15:23.158817+00:00"},{"alias_kind":"pith_short_8","alias_value":"56SRTPTY","created_at":"2026-07-05T05:15:23.158817+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/56SRTPTYZDZ55IQTXFCHEZ5AL5","json":"https://pith.science/pith/56SRTPTYZDZ55IQTXFCHEZ5AL5.json","graph_json":"https://pith.science/api/pith-number/56SRTPTYZDZ55IQTXFCHEZ5AL5/graph.json","events_json":"https://pith.science/api/pith-number/56SRTPTYZDZ55IQTXFCHEZ5AL5/events.json","paper":"https://pith.science/paper/56SRTPTY"},"agent_actions":{"view_html":"https://pith.science/pith/56SRTPTYZDZ55IQTXFCHEZ5AL5","download_json":"https://pith.science/pith/56SRTPTYZDZ55IQTXFCHEZ5AL5.json","view_paper":"https://pith.science/paper/56SRTPTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08669&json=true","fetch_graph":"https://pith.science/api/pith-number/56SRTPTYZDZ55IQTXFCHEZ5AL5/graph.json","fetch_events":"https://pith.science/api/pith-number/56SRTPTYZDZ55IQTXFCHEZ5AL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56SRTPTYZDZ55IQTXFCHEZ5AL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56SRTPTYZDZ55IQTXFCHEZ5AL5/action/storage_attestation","attest_author":"https://pith.science/pith/56SRTPTYZDZ55IQTXFCHEZ5AL5/action/author_attestation","sign_citation":"https://pith.science/pith/56SRTPTYZDZ55IQTXFCHEZ5AL5/action/citation_signature","submit_replication":"https://pith.science/pith/56SRTPTYZDZ55IQTXFCHEZ5AL5/action/replication_record"}},"created_at":"2026-07-05T05:15:23.158817+00:00","updated_at":"2026-07-05T05:15:23.158817+00:00"}