{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6GYHOTLODVTRVXZL6MKWVZX6XJ","short_pith_number":"pith:6GYHOTLO","schema_version":"1.0","canonical_sha256":"f1b0774d6e1d671adf2bf3156ae6feba63109e8af70caed918a5e01c97fc859e","source":{"kind":"arxiv","id":"2008.04277","version":1},"attestation_state":"computed","paper":{"title":"SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amitava Das, Bj\\\"orn Gamb\\\"ack, Gustavo Aguilar, Parth Patwa, Srinivas PYKL, Sudipta Kar, Suraj Pandey, Tanmoy Chakraborty, Thamar Solorio","submitted_at":"2020-08-10T17:17:52Z","abstract_excerpt":"In this paper, we present the results of the SemEval-2020 Task 9 on Sentiment Analysis of Code-Mixed Tweets (SentiMix 2020). We also release and describe our Hinglish (Hindi-English) and Spanglish (Spanish-English) corpora annotated with word-level language identification and sentence-level sentiment labels. These corpora are comprised of 20K and 19K examples, respectively. The sentiment labels are - Positive, Negative, and Neutral. SentiMix attracted 89 submissions in total including 61 teams that participated in the Hinglish contest and 28 submitted systems to the Spanglish competition. The "},"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":"2008.04277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T17:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"e2372520fbb2dea7c28486d9640cfc441d843239a4e4b5287ab844e7b08d6575","abstract_canon_sha256":"c30da292643e5a014b4a4d799a2d4514f591e8bbb86aa834e095bafce252cafd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:01.633568Z","signature_b64":"pFQiI6hBIgqLbRiQs0RmjinV8zmn09nWY6lty1KmeWtl1Y5l6nPbd2mtFjeX3xKddPKN2UiL5hR4hipSCrzmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1b0774d6e1d671adf2bf3156ae6feba63109e8af70caed918a5e01c97fc859e","last_reissued_at":"2026-07-05T01:26:01.633139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:01.633139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amitava Das, Bj\\\"orn Gamb\\\"ack, Gustavo Aguilar, Parth Patwa, Srinivas PYKL, Sudipta Kar, Suraj Pandey, Tanmoy Chakraborty, Thamar Solorio","submitted_at":"2020-08-10T17:17:52Z","abstract_excerpt":"In this paper, we present the results of the SemEval-2020 Task 9 on Sentiment Analysis of Code-Mixed Tweets (SentiMix 2020). We also release and describe our Hinglish (Hindi-English) and Spanglish (Spanish-English) corpora annotated with word-level language identification and sentence-level sentiment labels. These corpora are comprised of 20K and 19K examples, respectively. The sentiment labels are - Positive, Negative, and Neutral. SentiMix attracted 89 submissions in total including 61 teams that participated in the Hinglish contest and 28 submitted systems to the Spanglish competition. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04277","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/2008.04277/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":"2008.04277","created_at":"2026-07-05T01:26:01.633196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.04277v1","created_at":"2026-07-05T01:26:01.633196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04277","created_at":"2026-07-05T01:26:01.633196+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GYHOTLODVTR","created_at":"2026-07-05T01:26:01.633196+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GYHOTLODVTRVXZL","created_at":"2026-07-05T01:26:01.633196+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GYHOTLO","created_at":"2026-07-05T01:26:01.633196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09073","citing_title":"CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ","json":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ.json","graph_json":"https://pith.science/api/pith-number/6GYHOTLODVTRVXZL6MKWVZX6XJ/graph.json","events_json":"https://pith.science/api/pith-number/6GYHOTLODVTRVXZL6MKWVZX6XJ/events.json","paper":"https://pith.science/paper/6GYHOTLO"},"agent_actions":{"view_html":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ","download_json":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ.json","view_paper":"https://pith.science/paper/6GYHOTLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.04277&json=true","fetch_graph":"https://pith.science/api/pith-number/6GYHOTLODVTRVXZL6MKWVZX6XJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6GYHOTLODVTRVXZL6MKWVZX6XJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ/action/storage_attestation","attest_author":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ/action/author_attestation","sign_citation":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ/action/citation_signature","submit_replication":"https://pith.science/pith/6GYHOTLODVTRVXZL6MKWVZX6XJ/action/replication_record"}},"created_at":"2026-07-05T01:26:01.633196+00:00","updated_at":"2026-07-05T01:26:01.633196+00:00"}