{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RSRTJ6EN5UPNDJFOLN7C4BGVTZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"68b7ef904755e2bf5ae9e4382dcb11b6020e1c1d83bd4ac46d3e47a3e9517c1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T13:13:26Z","title_canon_sha256":"dad71ca160fb14828d4dbef6d46666e4fe317d9e33266eea61e19b12af6c1d37"},"schema_version":"1.0","source":{"id":"2106.09460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09460","created_at":"2026-07-05T04:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09460v1","created_at":"2026-07-05T04:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09460","created_at":"2026-07-05T04:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"RSRTJ6EN5UPN","created_at":"2026-07-05T04:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"RSRTJ6EN5UPNDJFO","created_at":"2026-07-05T04:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"RSRTJ6EN","created_at":"2026-07-05T04:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:689a764f4f5c097bae8250a105f2f27e0f8c9445248976e707dee9e62f3434ea","target":"graph","created_at":"2026-07-05T04:23:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.09460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bharathi Raja Chakravarthi, Elizabeth Sherly, John P. McCrae, Navya Jose, Ruba Priyadharshini, Shardul Suryawanshi, Vigneshwaran Muralidaran","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T13:13:26Z","title":"DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09460","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:95187e86a9a8996b273c88462d38fe369db40e909761bde0b49efffd8ea7bff9","target":"record","created_at":"2026-07-05T04:23:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"68b7ef904755e2bf5ae9e4382dcb11b6020e1c1d83bd4ac46d3e47a3e9517c1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T13:13:26Z","title_canon_sha256":"dad71ca160fb14828d4dbef6d46666e4fe317d9e33266eea61e19b12af6c1d37"},"schema_version":"1.0","source":{"id":"2106.09460","kind":"arxiv","version":1}},"canonical_sha256":"8ca334f88ded1ed1a4ae5b7e2e04d59e4deb4b501781c1ccd0feb22f61f7891e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ca334f88ded1ed1a4ae5b7e2e04d59e4deb4b501781c1ccd0feb22f61f7891e","first_computed_at":"2026-07-05T04:23:20.764881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:23:20.764881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+38n6foTajS0qd9SgucILzJdc++ZcZblwHEl4fpQQv3QO7m7D+blfiPXmauJCLLUNnlGYq2RWQPgfxn/laswBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:23:20.765396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95187e86a9a8996b273c88462d38fe369db40e909761bde0b49efffd8ea7bff9","sha256:689a764f4f5c097bae8250a105f2f27e0f8c9445248976e707dee9e62f3434ea"],"state_sha256":"c013fdc0669f32b10da7ef2ee0008ce8316a4ecc10a92c7d863ad10f4099ec5c"}