{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CJOU5MKSXIPTIFQ2HSDXVPPZQE","short_pith_number":"pith:CJOU5MKS","schema_version":"1.0","canonical_sha256":"125d4eb152ba1f34161a3c877abdf98118929dbd3733943145a49b7f3f07339d","source":{"kind":"arxiv","id":"2310.02249","version":1},"attestation_state":"computed","paper":{"title":"Harnessing Pre-Trained Sentence Transformers for Offensive Language Detection in Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ananya Joshi, Raviraj Joshi","submitted_at":"2023-10-03T17:53:09Z","abstract_excerpt":"In our increasingly interconnected digital world, social media platforms have emerged as powerful channels for the dissemination of hate speech and offensive content. This work delves into the domain of hate speech detection, placing specific emphasis on three low-resource Indian languages: Bengali, Assamese, and Gujarati. The challenge is framed as a text classification task, aimed at discerning whether a tweet contains offensive or non-offensive content. Leveraging the HASOC 2023 datasets, we fine-tuned pre-trained BERT and SBERT models to evaluate their effectiveness in identifying hate spe"},"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":"2310.02249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T17:53:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e5a90923365beeff0052f88cbcdaa76397bcb9a60050669d4566ea5aedee565","abstract_canon_sha256":"81fde46ee5ab78552c2a210e57b9cf680b780dfdec1df0f5bad673df393adfbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:51.889843Z","signature_b64":"f3v3dIKac19kqf4TtVRUfxdPifdZ2MtqyoFYjgK/iJaan4mIQC+rPv4eJoOxinuW1xY8G9c2L48egyX4IIJkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"125d4eb152ba1f34161a3c877abdf98118929dbd3733943145a49b7f3f07339d","last_reissued_at":"2026-07-05T06:56:51.889371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:51.889371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Pre-Trained Sentence Transformers for Offensive Language Detection in Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ananya Joshi, Raviraj Joshi","submitted_at":"2023-10-03T17:53:09Z","abstract_excerpt":"In our increasingly interconnected digital world, social media platforms have emerged as powerful channels for the dissemination of hate speech and offensive content. This work delves into the domain of hate speech detection, placing specific emphasis on three low-resource Indian languages: Bengali, Assamese, and Gujarati. The challenge is framed as a text classification task, aimed at discerning whether a tweet contains offensive or non-offensive content. Leveraging the HASOC 2023 datasets, we fine-tuned pre-trained BERT and SBERT models to evaluate their effectiveness in identifying hate spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02249","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/2310.02249/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":"2310.02249","created_at":"2026-07-05T06:56:51.889430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02249v1","created_at":"2026-07-05T06:56:51.889430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02249","created_at":"2026-07-05T06:56:51.889430+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJOU5MKSXIPT","created_at":"2026-07-05T06:56:51.889430+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJOU5MKSXIPTIFQ2","created_at":"2026-07-05T06:56:51.889430+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJOU5MKS","created_at":"2026-07-05T06:56:51.889430+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/CJOU5MKSXIPTIFQ2HSDXVPPZQE","json":"https://pith.science/pith/CJOU5MKSXIPTIFQ2HSDXVPPZQE.json","graph_json":"https://pith.science/api/pith-number/CJOU5MKSXIPTIFQ2HSDXVPPZQE/graph.json","events_json":"https://pith.science/api/pith-number/CJOU5MKSXIPTIFQ2HSDXVPPZQE/events.json","paper":"https://pith.science/paper/CJOU5MKS"},"agent_actions":{"view_html":"https://pith.science/pith/CJOU5MKSXIPTIFQ2HSDXVPPZQE","download_json":"https://pith.science/pith/CJOU5MKSXIPTIFQ2HSDXVPPZQE.json","view_paper":"https://pith.science/paper/CJOU5MKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02249&json=true","fetch_graph":"https://pith.science/api/pith-number/CJOU5MKSXIPTIFQ2HSDXVPPZQE/graph.json","fetch_events":"https://pith.science/api/pith-number/CJOU5MKSXIPTIFQ2HSDXVPPZQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJOU5MKSXIPTIFQ2HSDXVPPZQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJOU5MKSXIPTIFQ2HSDXVPPZQE/action/storage_attestation","attest_author":"https://pith.science/pith/CJOU5MKSXIPTIFQ2HSDXVPPZQE/action/author_attestation","sign_citation":"https://pith.science/pith/CJOU5MKSXIPTIFQ2HSDXVPPZQE/action/citation_signature","submit_replication":"https://pith.science/pith/CJOU5MKSXIPTIFQ2HSDXVPPZQE/action/replication_record"}},"created_at":"2026-07-05T06:56:51.889430+00:00","updated_at":"2026-07-05T06:56:51.889430+00:00"}