{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W4KEFTDQDJNLWQSM2ITBHECG5W","short_pith_number":"pith:W4KEFTDQ","schema_version":"1.0","canonical_sha256":"b71442cc701a5abb424cd226139046edb722a010af31332abb9b5a2ed573bd9e","source":{"kind":"arxiv","id":"2305.13821","version":1},"attestation_state":"computed","paper":{"title":"GenSpectrum Chat: Data Exploration in Public Health Using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"q-bio.GN","authors_text":"Chaoran Chen, Tanja Stadler","submitted_at":"2023-05-23T08:43:43Z","abstract_excerpt":"Introduction: The COVID-19 pandemic highlighted the importance of making epidemiological data and scientific insights easily accessible and explorable for public health agencies, the general public, and researchers. State-of-the-art approaches for sharing data and insights included regularly updated reports and web dashboards. However, they face a trade-off between the simplicity and flexibility of data exploration. With the capabilities of recent large language models (LLMs) such as GPT-4, this trade-off can be overcome.\n  Results: We developed the chatbot \"GenSpectrum Chat\" (https://cov-spec"},"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":"2305.13821","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2023-05-23T08:43:43Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"2b011cb8973feb5e0c3063f476fd75be701ace4582813d325afc8516c7169497","abstract_canon_sha256":"c8fc11932e8b2c4a73b989ae81edd27df481bb092259bf3b43c7a241214b53f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:57.861156Z","signature_b64":"baTDrQ3cJB7+fgo1vzGDatFGlaKmF0fNlFWNw2zsoEYKJxRqt+t9Yqg5XmNpQIHx/C5MR7/ZlJSVyLI1ac5DDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b71442cc701a5abb424cd226139046edb722a010af31332abb9b5a2ed573bd9e","last_reissued_at":"2026-07-05T06:12:57.860724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:57.860724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenSpectrum Chat: Data Exploration in Public Health Using Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"q-bio.GN","authors_text":"Chaoran Chen, Tanja Stadler","submitted_at":"2023-05-23T08:43:43Z","abstract_excerpt":"Introduction: The COVID-19 pandemic highlighted the importance of making epidemiological data and scientific insights easily accessible and explorable for public health agencies, the general public, and researchers. State-of-the-art approaches for sharing data and insights included regularly updated reports and web dashboards. However, they face a trade-off between the simplicity and flexibility of data exploration. With the capabilities of recent large language models (LLMs) such as GPT-4, this trade-off can be overcome.\n  Results: We developed the chatbot \"GenSpectrum Chat\" (https://cov-spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13821","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/2305.13821/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":"2305.13821","created_at":"2026-07-05T06:12:57.860781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13821v1","created_at":"2026-07-05T06:12:57.860781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13821","created_at":"2026-07-05T06:12:57.860781+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4KEFTDQDJNL","created_at":"2026-07-05T06:12:57.860781+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4KEFTDQDJNLWQSM","created_at":"2026-07-05T06:12:57.860781+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4KEFTDQ","created_at":"2026-07-05T06:12:57.860781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02628","citing_title":"A Generative Approach for Semantic Auditing of Electronic Health Records","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W","json":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W.json","graph_json":"https://pith.science/api/pith-number/W4KEFTDQDJNLWQSM2ITBHECG5W/graph.json","events_json":"https://pith.science/api/pith-number/W4KEFTDQDJNLWQSM2ITBHECG5W/events.json","paper":"https://pith.science/paper/W4KEFTDQ"},"agent_actions":{"view_html":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W","download_json":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W.json","view_paper":"https://pith.science/paper/W4KEFTDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13821&json=true","fetch_graph":"https://pith.science/api/pith-number/W4KEFTDQDJNLWQSM2ITBHECG5W/graph.json","fetch_events":"https://pith.science/api/pith-number/W4KEFTDQDJNLWQSM2ITBHECG5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W/action/storage_attestation","attest_author":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W/action/author_attestation","sign_citation":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W/action/citation_signature","submit_replication":"https://pith.science/pith/W4KEFTDQDJNLWQSM2ITBHECG5W/action/replication_record"}},"created_at":"2026-07-05T06:12:57.860781+00:00","updated_at":"2026-07-05T06:12:57.860781+00:00"}