{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJTB45AKUEN67CPIMXFZEJL7YT","short_pith_number":"pith:BJTB45AK","schema_version":"1.0","canonical_sha256":"0a661e740aa11bef89e865cb92257fc4f07935bbc1898019d92b90b1a4a1317b","source":{"kind":"arxiv","id":"2405.20755","version":2},"attestation_state":"computed","paper":{"title":"Improving code-mixed hate detection by native sample mixing: A case study for Hindi-English code-mixed scenario","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aakash Kumar, Debajyoti Mazumder, Jasabanta Patro","submitted_at":"2024-05-31T11:43:31Z","abstract_excerpt":"Hate detection has long been a challenging task for the NLP community. The task becomes complex in a code-mixed environment because the models must understand the context and the hate expressed through language alteration. Compared to the monolingual setup, we see much less work on code-mixed hate as large-scale annotated hate corpora are unavailable for the study. To overcome this bottleneck, we propose using native language hate samples (native language samples/ native samples hereafter). We hypothesise that in the era of multilingual language models (MLMs), hate in code-mixed settings can b"},"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":"2405.20755","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T11:43:31Z","cross_cats_sorted":[],"title_canon_sha256":"2a39cd71cc8f230a8452c2524a7e2b3d3eba5f4a7f9a3aeabc069460c623b23e","abstract_canon_sha256":"b8153b9f656fa5096138fe6cbb16c4d3ecb956e68b206cd96354615b4628cdfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:06.450687Z","signature_b64":"aOE3/2lX2A9yidalEJOjvEZfLnVCppEYuK5wT8DmrPd1WfETWepwBLSUSaZ2dbw7wxOuTQY9bY4Q4zeVpAVUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a661e740aa11bef89e865cb92257fc4f07935bbc1898019d92b90b1a4a1317b","last_reissued_at":"2026-07-05T09:23:06.450264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:06.450264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving code-mixed hate detection by native sample mixing: A case study for Hindi-English code-mixed scenario","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aakash Kumar, Debajyoti Mazumder, Jasabanta Patro","submitted_at":"2024-05-31T11:43:31Z","abstract_excerpt":"Hate detection has long been a challenging task for the NLP community. The task becomes complex in a code-mixed environment because the models must understand the context and the hate expressed through language alteration. Compared to the monolingual setup, we see much less work on code-mixed hate as large-scale annotated hate corpora are unavailable for the study. To overcome this bottleneck, we propose using native language hate samples (native language samples/ native samples hereafter). We hypothesise that in the era of multilingual language models (MLMs), hate in code-mixed settings can b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20755","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/2405.20755/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":"2405.20755","created_at":"2026-07-05T09:23:06.450327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20755v2","created_at":"2026-07-05T09:23:06.450327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20755","created_at":"2026-07-05T09:23:06.450327+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJTB45AKUEN6","created_at":"2026-07-05T09:23:06.450327+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJTB45AKUEN67CPI","created_at":"2026-07-05T09:23:06.450327+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJTB45AK","created_at":"2026-07-05T09:23:06.450327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12761","citing_title":"Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT","json":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT.json","graph_json":"https://pith.science/api/pith-number/BJTB45AKUEN67CPIMXFZEJL7YT/graph.json","events_json":"https://pith.science/api/pith-number/BJTB45AKUEN67CPIMXFZEJL7YT/events.json","paper":"https://pith.science/paper/BJTB45AK"},"agent_actions":{"view_html":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT","download_json":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT.json","view_paper":"https://pith.science/paper/BJTB45AK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20755&json=true","fetch_graph":"https://pith.science/api/pith-number/BJTB45AKUEN67CPIMXFZEJL7YT/graph.json","fetch_events":"https://pith.science/api/pith-number/BJTB45AKUEN67CPIMXFZEJL7YT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT/action/storage_attestation","attest_author":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT/action/author_attestation","sign_citation":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT/action/citation_signature","submit_replication":"https://pith.science/pith/BJTB45AKUEN67CPIMXFZEJL7YT/action/replication_record"}},"created_at":"2026-07-05T09:23:06.450327+00:00","updated_at":"2026-07-05T09:23:06.450327+00:00"}