{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RSRTJ6EN5UPNDJFOLN7C4BGVTZ","short_pith_number":"pith:RSRTJ6EN","schema_version":"1.0","canonical_sha256":"8ca334f88ded1ed1a4ae5b7e2e04d59e4deb4b501781c1ccd0feb22f61f7891e","source":{"kind":"arxiv","id":"2106.09460","version":1},"attestation_state":"computed","paper":{"title":"DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bharathi Raja Chakravarthi, Elizabeth Sherly, John P. McCrae, Navya Jose, Ruba Priyadharshini, Shardul Suryawanshi, Vigneshwaran Muralidaran","submitted_at":"2021-06-17T13:13:26Z","abstract_excerpt":"This paper describes the development of a multilingual, manually annotated dataset for three under-resourced Dravidian languages generated from social media comments. The dataset was annotated for sentiment analysis and offensive language identification for a total of more than 60,000 YouTube comments. The dataset consists of around 44,000 comments in Tamil-English, around 7,000 comments in Kannada-English, and around 20,000 comments in Malayalam-English. The data was manually annotated by volunteer annotators and has a high inter-annotator agreement in Krippendorff's alpha. The dataset contai"},"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":"2106.09460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T13:13:26Z","cross_cats_sorted":[],"title_canon_sha256":"dad71ca160fb14828d4dbef6d46666e4fe317d9e33266eea61e19b12af6c1d37","abstract_canon_sha256":"68b7ef904755e2bf5ae9e4382dcb11b6020e1c1d83bd4ac46d3e47a3e9517c1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:20.765396Z","signature_b64":"+38n6foTajS0qd9SgucILzJdc++ZcZblwHEl4fpQQv3QO7m7D+blfiPXmauJCLLUNnlGYq2RWQPgfxn/laswBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ca334f88ded1ed1a4ae5b7e2e04d59e4deb4b501781c1ccd0feb22f61f7891e","last_reissued_at":"2026-07-05T04:23:20.764881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:20.764881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bharathi Raja Chakravarthi, Elizabeth Sherly, John P. McCrae, Navya Jose, Ruba Priyadharshini, Shardul Suryawanshi, Vigneshwaran Muralidaran","submitted_at":"2021-06-17T13:13:26Z","abstract_excerpt":"This paper describes the development of a multilingual, manually annotated dataset for three under-resourced Dravidian languages generated from social media comments. The dataset was annotated for sentiment analysis and offensive language identification for a total of more than 60,000 YouTube comments. The dataset consists of around 44,000 comments in Tamil-English, around 7,000 comments in Kannada-English, and around 20,000 comments in Malayalam-English. The data was manually annotated by volunteer annotators and has a high inter-annotator agreement in Krippendorff's alpha. The dataset contai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09460","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/2106.09460/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":"2106.09460","created_at":"2026-07-05T04:23:20.764943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09460v1","created_at":"2026-07-05T04:23:20.764943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09460","created_at":"2026-07-05T04:23:20.764943+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSRTJ6EN5UPN","created_at":"2026-07-05T04:23:20.764943+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSRTJ6EN5UPNDJFO","created_at":"2026-07-05T04:23:20.764943+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSRTJ6EN","created_at":"2026-07-05T04:23:20.764943+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/RSRTJ6EN5UPNDJFOLN7C4BGVTZ","json":"https://pith.science/pith/RSRTJ6EN5UPNDJFOLN7C4BGVTZ.json","graph_json":"https://pith.science/api/pith-number/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/graph.json","events_json":"https://pith.science/api/pith-number/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/events.json","paper":"https://pith.science/paper/RSRTJ6EN"},"agent_actions":{"view_html":"https://pith.science/pith/RSRTJ6EN5UPNDJFOLN7C4BGVTZ","download_json":"https://pith.science/pith/RSRTJ6EN5UPNDJFOLN7C4BGVTZ.json","view_paper":"https://pith.science/paper/RSRTJ6EN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09460&json=true","fetch_graph":"https://pith.science/api/pith-number/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/action/storage_attestation","attest_author":"https://pith.science/pith/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/action/author_attestation","sign_citation":"https://pith.science/pith/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/action/citation_signature","submit_replication":"https://pith.science/pith/RSRTJ6EN5UPNDJFOLN7C4BGVTZ/action/replication_record"}},"created_at":"2026-07-05T04:23:20.764943+00:00","updated_at":"2026-07-05T04:23:20.764943+00:00"}