{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B3X7AMSM4UHBQI27CSVWJRTGU7","short_pith_number":"pith:B3X7AMSM","schema_version":"1.0","canonical_sha256":"0eeff0324ce50e18235f14ab64c666a7f76ccd17c5e79042a0410c2308c90d59","source":{"kind":"arxiv","id":"2403.19031","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Large Language Models for Health-Related Text Classification Tasks with Public Social Media Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abeed Sarker, Anthony Ovadje, Mohammed Ali Al-Garadi, Yuting Guo","submitted_at":"2024-03-27T22:05:10Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable success in NLP tasks. However, there is a paucity of studies that attempt to evaluate their performances on social media-based health-related natural language processing tasks, which have traditionally been difficult to achieve high scores in. We benchmarked one supervised classic machine learning model based on Support Vector Machines (SVMs), three supervised pretrained language models (PLMs) based on RoBERTa, BERTweet, and SocBERT, and two LLM based classifiers (GPT3.5 and GPT4), across 6 text classification tasks. We developed three "},"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":"2403.19031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-27T22:05:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"47c88c050d166e30cbfcbb62d28fb6b85c2767e4e528bdfdad09abb4b0f29777","abstract_canon_sha256":"2a498b2a60d7166c1b6adc14074b728826333f42e329e31beefbf20f460767a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:43.209396Z","signature_b64":"4+nd8N+pf4kyOa86lqP2Kx3+1BqhNsEfh1nM+pchK67kZ7l6C63NAbMMPoYhZXgGzNBTT/3TdFa8rjXVwswEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eeff0324ce50e18235f14ab64c666a7f76ccd17c5e79042a0410c2308c90d59","last_reissued_at":"2026-07-05T08:01:43.208970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:43.208970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Large Language Models for Health-Related Text Classification Tasks with Public Social Media Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abeed Sarker, Anthony Ovadje, Mohammed Ali Al-Garadi, Yuting Guo","submitted_at":"2024-03-27T22:05:10Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable success in NLP tasks. However, there is a paucity of studies that attempt to evaluate their performances on social media-based health-related natural language processing tasks, which have traditionally been difficult to achieve high scores in. We benchmarked one supervised classic machine learning model based on Support Vector Machines (SVMs), three supervised pretrained language models (PLMs) based on RoBERTa, BERTweet, and SocBERT, and two LLM based classifiers (GPT3.5 and GPT4), across 6 text classification tasks. We developed three "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19031","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/2403.19031/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":"2403.19031","created_at":"2026-07-05T08:01:43.209039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19031v1","created_at":"2026-07-05T08:01:43.209039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19031","created_at":"2026-07-05T08:01:43.209039+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3X7AMSM4UHB","created_at":"2026-07-05T08:01:43.209039+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3X7AMSM4UHBQI27","created_at":"2026-07-05T08:01:43.209039+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3X7AMSM","created_at":"2026-07-05T08:01:43.209039+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/B3X7AMSM4UHBQI27CSVWJRTGU7","json":"https://pith.science/pith/B3X7AMSM4UHBQI27CSVWJRTGU7.json","graph_json":"https://pith.science/api/pith-number/B3X7AMSM4UHBQI27CSVWJRTGU7/graph.json","events_json":"https://pith.science/api/pith-number/B3X7AMSM4UHBQI27CSVWJRTGU7/events.json","paper":"https://pith.science/paper/B3X7AMSM"},"agent_actions":{"view_html":"https://pith.science/pith/B3X7AMSM4UHBQI27CSVWJRTGU7","download_json":"https://pith.science/pith/B3X7AMSM4UHBQI27CSVWJRTGU7.json","view_paper":"https://pith.science/paper/B3X7AMSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19031&json=true","fetch_graph":"https://pith.science/api/pith-number/B3X7AMSM4UHBQI27CSVWJRTGU7/graph.json","fetch_events":"https://pith.science/api/pith-number/B3X7AMSM4UHBQI27CSVWJRTGU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3X7AMSM4UHBQI27CSVWJRTGU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3X7AMSM4UHBQI27CSVWJRTGU7/action/storage_attestation","attest_author":"https://pith.science/pith/B3X7AMSM4UHBQI27CSVWJRTGU7/action/author_attestation","sign_citation":"https://pith.science/pith/B3X7AMSM4UHBQI27CSVWJRTGU7/action/citation_signature","submit_replication":"https://pith.science/pith/B3X7AMSM4UHBQI27CSVWJRTGU7/action/replication_record"}},"created_at":"2026-07-05T08:01:43.209039+00:00","updated_at":"2026-07-05T08:01:43.209039+00:00"}