{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WQNNWH35W7RXYTJMXNNTZWACJM","short_pith_number":"pith:WQNNWH35","schema_version":"1.0","canonical_sha256":"b41adb1f7db7e37c4d2cbb5b3cd8024b013ce0f79fc3e922c279d37ada997575","source":{"kind":"arxiv","id":"2502.06150","version":1},"attestation_state":"computed","paper":{"title":"Scaling Public Health Text Annotation: Zero-Shot Learning vs. Crowdsourcing for Improved Efficiency and Labeling Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kamyar Kazari, Yong Chen, Zahra Shakeri","submitted_at":"2025-02-10T04:33:27Z","abstract_excerpt":"Public health researchers are increasingly interested in using social media data to study health-related behaviors, but manually labeling this data can be labor-intensive and costly. This study explores whether zero-shot labeling using large language models (LLMs) can match or surpass conventional crowd-sourced annotation for Twitter posts related to sleep disorders, physical activity, and sedentary behavior. Multiple annotation pipelines were designed to compare labels produced by domain experts, crowd workers, and LLM-driven approaches under varied prompt-engineering strategies. Our findings"},"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":"2502.06150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T04:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"f915c0a46282312bf314b5df10d12761169fa3f42f30a04df270cd2e92fc1586","abstract_canon_sha256":"b9347498dbdbb7d405324e75790dac11a270b1730ae8fc231e614bf3da3ba7c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:48.393279Z","signature_b64":"Ngv14QemAQY6Xe0rqYGPoAgU17bP4DnzvADwsDDEuROFQNKKUoDeESmUr/kIEkib320Ra1zDb6sAKoBsI6fkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b41adb1f7db7e37c4d2cbb5b3cd8024b013ce0f79fc3e922c279d37ada997575","last_reissued_at":"2026-07-05T10:11:48.392816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:48.392816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Public Health Text Annotation: Zero-Shot Learning vs. Crowdsourcing for Improved Efficiency and Labeling Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kamyar Kazari, Yong Chen, Zahra Shakeri","submitted_at":"2025-02-10T04:33:27Z","abstract_excerpt":"Public health researchers are increasingly interested in using social media data to study health-related behaviors, but manually labeling this data can be labor-intensive and costly. This study explores whether zero-shot labeling using large language models (LLMs) can match or surpass conventional crowd-sourced annotation for Twitter posts related to sleep disorders, physical activity, and sedentary behavior. Multiple annotation pipelines were designed to compare labels produced by domain experts, crowd workers, and LLM-driven approaches under varied prompt-engineering strategies. Our findings"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06150","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/2502.06150/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":"2502.06150","created_at":"2026-07-05T10:11:48.392868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06150v1","created_at":"2026-07-05T10:11:48.392868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06150","created_at":"2026-07-05T10:11:48.392868+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQNNWH35W7RX","created_at":"2026-07-05T10:11:48.392868+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQNNWH35W7RXYTJM","created_at":"2026-07-05T10:11:48.392868+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQNNWH35","created_at":"2026-07-05T10:11:48.392868+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/WQNNWH35W7RXYTJMXNNTZWACJM","json":"https://pith.science/pith/WQNNWH35W7RXYTJMXNNTZWACJM.json","graph_json":"https://pith.science/api/pith-number/WQNNWH35W7RXYTJMXNNTZWACJM/graph.json","events_json":"https://pith.science/api/pith-number/WQNNWH35W7RXYTJMXNNTZWACJM/events.json","paper":"https://pith.science/paper/WQNNWH35"},"agent_actions":{"view_html":"https://pith.science/pith/WQNNWH35W7RXYTJMXNNTZWACJM","download_json":"https://pith.science/pith/WQNNWH35W7RXYTJMXNNTZWACJM.json","view_paper":"https://pith.science/paper/WQNNWH35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06150&json=true","fetch_graph":"https://pith.science/api/pith-number/WQNNWH35W7RXYTJMXNNTZWACJM/graph.json","fetch_events":"https://pith.science/api/pith-number/WQNNWH35W7RXYTJMXNNTZWACJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQNNWH35W7RXYTJMXNNTZWACJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQNNWH35W7RXYTJMXNNTZWACJM/action/storage_attestation","attest_author":"https://pith.science/pith/WQNNWH35W7RXYTJMXNNTZWACJM/action/author_attestation","sign_citation":"https://pith.science/pith/WQNNWH35W7RXYTJMXNNTZWACJM/action/citation_signature","submit_replication":"https://pith.science/pith/WQNNWH35W7RXYTJMXNNTZWACJM/action/replication_record"}},"created_at":"2026-07-05T10:11:48.392868+00:00","updated_at":"2026-07-05T10:11:48.392868+00:00"}