{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UXOYEPZBATISLPU6X6IRPP3JK7","short_pith_number":"pith:UXOYEPZB","schema_version":"1.0","canonical_sha256":"a5dd823f2104d125be9ebf9117bf6957ff30fd49124fcc28d59723e52bf841ce","source":{"kind":"arxiv","id":"2008.09820","version":1},"attestation_state":"computed","paper":{"title":"HinglishNLP: Fine-tuned Language Models for Hinglish Sentiment Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Meghana Bhange, Nirant Kasliwal","submitted_at":"2020-08-22T12:01:44Z","abstract_excerpt":"Sentiment analysis for code-mixed social media text continues to be an under-explored area. This work adds two common approaches: fine-tuning large transformer models and sample efficient methods like ULMFiT. Prior work demonstrates the efficacy of classical ML methods for polarity detection. Fine-tuned general-purpose language representation models, such as those of the BERT family are benchmarked along with classical machine learning and ensemble methods. We show that NB-SVM beats RoBERTa by 6.2% (relative) F1. The best performing model is a majority-vote ensemble which achieves an F1 of 0.7"},"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":"2008.09820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-22T12:01:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5be2afd331ac3ff1ff997c5a1d1b4d4f2badf2f751119edff6bd4104debb0fff","abstract_canon_sha256":"eaa32d3c2f3e23832b890c6f22e86b756be70baaa2fa7d233852618e20b7dfe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:17.520472Z","signature_b64":"hTMhFHBwxntr5BGP6MkIufk85JP67kSTNnY+G36Ma6Kx7wwrwDfaXCuldmzEr/YfvhokTB0FBwoQIWpCHfkcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5dd823f2104d125be9ebf9117bf6957ff30fd49124fcc28d59723e52bf841ce","last_reissued_at":"2026-07-05T01:29:17.520062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:17.520062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HinglishNLP: Fine-tuned Language Models for Hinglish Sentiment Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Meghana Bhange, Nirant Kasliwal","submitted_at":"2020-08-22T12:01:44Z","abstract_excerpt":"Sentiment analysis for code-mixed social media text continues to be an under-explored area. This work adds two common approaches: fine-tuning large transformer models and sample efficient methods like ULMFiT. Prior work demonstrates the efficacy of classical ML methods for polarity detection. Fine-tuned general-purpose language representation models, such as those of the BERT family are benchmarked along with classical machine learning and ensemble methods. We show that NB-SVM beats RoBERTa by 6.2% (relative) F1. The best performing model is a majority-vote ensemble which achieves an F1 of 0.7"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09820","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/2008.09820/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":"2008.09820","created_at":"2026-07-05T01:29:17.520122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.09820v1","created_at":"2026-07-05T01:29:17.520122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09820","created_at":"2026-07-05T01:29:17.520122+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXOYEPZBATIS","created_at":"2026-07-05T01:29:17.520122+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXOYEPZBATISLPU6","created_at":"2026-07-05T01:29:17.520122+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXOYEPZB","created_at":"2026-07-05T01:29:17.520122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07292","citing_title":"Multimodal Sentiment Analysis Based on Causal Reasoning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7","json":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7.json","graph_json":"https://pith.science/api/pith-number/UXOYEPZBATISLPU6X6IRPP3JK7/graph.json","events_json":"https://pith.science/api/pith-number/UXOYEPZBATISLPU6X6IRPP3JK7/events.json","paper":"https://pith.science/paper/UXOYEPZB"},"agent_actions":{"view_html":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7","download_json":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7.json","view_paper":"https://pith.science/paper/UXOYEPZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.09820&json=true","fetch_graph":"https://pith.science/api/pith-number/UXOYEPZBATISLPU6X6IRPP3JK7/graph.json","fetch_events":"https://pith.science/api/pith-number/UXOYEPZBATISLPU6X6IRPP3JK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7/action/storage_attestation","attest_author":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7/action/author_attestation","sign_citation":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7/action/citation_signature","submit_replication":"https://pith.science/pith/UXOYEPZBATISLPU6X6IRPP3JK7/action/replication_record"}},"created_at":"2026-07-05T01:29:17.520122+00:00","updated_at":"2026-07-05T01:29:17.520122+00:00"}