{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z5K4UZRWNCNH6BJOBPECI4SURH","short_pith_number":"pith:Z5K4UZRW","schema_version":"1.0","canonical_sha256":"cf55ca6636689a7f052e0bc824725489d29b8176e089d2f442f2675bce356690","source":{"kind":"arxiv","id":"2107.12565","version":1},"attestation_state":"computed","paper":{"title":"A Biomedically oriented automatically annotated Twitter COVID-19 Dataset","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.IR","authors_text":"Juan M. Banda, Luis Alberto Robles Hernandez, Tiffany J. Callahan","submitted_at":"2021-07-27T02:58:34Z","abstract_excerpt":"The use of social media data, like Twitter, for biomedical research has been gradually increasing over the years. With the COVID-19 pandemic, researchers have turned to more nontraditional sources of clinical data to characterize the disease in near real-time, study the societal implications of interventions, as well as the sequelae that recovered COVID-19 cases present (Long-COVID). However, manually curated social media datasets are difficult to come by due to the expensive costs of manual annotation and the efforts needed to identify the correct texts. When datasets are available, they are "},"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":"2107.12565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-07-27T02:58:34Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"5c29103d4eb9ebff581f0a4e231f5252385bd0cead0d142213a33aaa8e6e1a3c","abstract_canon_sha256":"aae9e0aac64eeea466101499b0628c70736ecb36c2f1ee21d1daf1673fe02c75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:57.702629Z","signature_b64":"4xuSgctj6+/Kf7bYFR9heRs9Y0x6lbFo1v3/bVx6uv/q0iFpOkGOe4uO3v3ynGKvLsjs2cmiZ0kqDHiZakFHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf55ca6636689a7f052e0bc824725489d29b8176e089d2f442f2675bce356690","last_reissued_at":"2026-07-05T03:00:57.702255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:57.702255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Biomedically oriented automatically annotated Twitter COVID-19 Dataset","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.IR","authors_text":"Juan M. Banda, Luis Alberto Robles Hernandez, Tiffany J. Callahan","submitted_at":"2021-07-27T02:58:34Z","abstract_excerpt":"The use of social media data, like Twitter, for biomedical research has been gradually increasing over the years. With the COVID-19 pandemic, researchers have turned to more nontraditional sources of clinical data to characterize the disease in near real-time, study the societal implications of interventions, as well as the sequelae that recovered COVID-19 cases present (Long-COVID). However, manually curated social media datasets are difficult to come by due to the expensive costs of manual annotation and the efforts needed to identify the correct texts. When datasets are available, they are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12565","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/2107.12565/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":"2107.12565","created_at":"2026-07-05T03:00:57.702310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12565v1","created_at":"2026-07-05T03:00:57.702310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12565","created_at":"2026-07-05T03:00:57.702310+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5K4UZRWNCNH","created_at":"2026-07-05T03:00:57.702310+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5K4UZRWNCNH6BJO","created_at":"2026-07-05T03:00:57.702310+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5K4UZRW","created_at":"2026-07-05T03:00:57.702310+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/Z5K4UZRWNCNH6BJOBPECI4SURH","json":"https://pith.science/pith/Z5K4UZRWNCNH6BJOBPECI4SURH.json","graph_json":"https://pith.science/api/pith-number/Z5K4UZRWNCNH6BJOBPECI4SURH/graph.json","events_json":"https://pith.science/api/pith-number/Z5K4UZRWNCNH6BJOBPECI4SURH/events.json","paper":"https://pith.science/paper/Z5K4UZRW"},"agent_actions":{"view_html":"https://pith.science/pith/Z5K4UZRWNCNH6BJOBPECI4SURH","download_json":"https://pith.science/pith/Z5K4UZRWNCNH6BJOBPECI4SURH.json","view_paper":"https://pith.science/paper/Z5K4UZRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12565&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5K4UZRWNCNH6BJOBPECI4SURH/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5K4UZRWNCNH6BJOBPECI4SURH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5K4UZRWNCNH6BJOBPECI4SURH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5K4UZRWNCNH6BJOBPECI4SURH/action/storage_attestation","attest_author":"https://pith.science/pith/Z5K4UZRWNCNH6BJOBPECI4SURH/action/author_attestation","sign_citation":"https://pith.science/pith/Z5K4UZRWNCNH6BJOBPECI4SURH/action/citation_signature","submit_replication":"https://pith.science/pith/Z5K4UZRWNCNH6BJOBPECI4SURH/action/replication_record"}},"created_at":"2026-07-05T03:00:57.702310+00:00","updated_at":"2026-07-05T03:00:57.702310+00:00"}