{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PH42EG76P53ADKQLQIRNXSXGTK","short_pith_number":"pith:PH42EG76","schema_version":"1.0","canonical_sha256":"79f9a21bfe7f7601aa0b8222dbcae69a8582ac4457c5a0ad539bed0422a141bc","source":{"kind":"arxiv","id":"2504.11740","version":1},"attestation_state":"computed","paper":{"title":"A cautionary note for plasmode simulation studies in the setting of causal inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Brian D. Williamson, Chloe Krakauer, Jennifer C. Nelson, Mark J. van der Laan, Pamela A Shaw, Rishi Desai, Susan Gruber, Susan M. Shortreed","submitted_at":"2025-04-16T03:36:27Z","abstract_excerpt":"Plasmode simulation has become an important tool for evaluating the operating characteristics of different statistical methods in complex settings, such as pharmacoepidemiological studies of treatment effectiveness using electronic health records (EHR) data. These studies provide insight into how estimator performance is impacted by challenges including rare events, small sample size, etc., that can indicate which among a set of methods performs best in a real-world dataset. Plasmode simulation combines data resampled from a real-world dataset with synthetic data to generate a known truth for "},"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":"2504.11740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2025-04-16T03:36:27Z","cross_cats_sorted":[],"title_canon_sha256":"ccafa09275b5697706f2dd46c89e133a841807ef65acea330f3cfa32d857cbe4","abstract_canon_sha256":"6c85ea06b63cad499103bf0dc1359915976d2f90646aa51adc2ae1a309cdca1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:56.720806Z","signature_b64":"mnso5T6mE7k9j1HdoFDGy24kplIjdhSsWb9isXNvaQ9o7sfMBD/uBH8ICTWwUO73F0xYagmuNpaYLWZsJQiaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79f9a21bfe7f7601aa0b8222dbcae69a8582ac4457c5a0ad539bed0422a141bc","last_reissued_at":"2026-07-05T10:49:56.720204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:56.720204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A cautionary note for plasmode simulation studies in the setting of causal inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Brian D. Williamson, Chloe Krakauer, Jennifer C. Nelson, Mark J. van der Laan, Pamela A Shaw, Rishi Desai, Susan Gruber, Susan M. Shortreed","submitted_at":"2025-04-16T03:36:27Z","abstract_excerpt":"Plasmode simulation has become an important tool for evaluating the operating characteristics of different statistical methods in complex settings, such as pharmacoepidemiological studies of treatment effectiveness using electronic health records (EHR) data. These studies provide insight into how estimator performance is impacted by challenges including rare events, small sample size, etc., that can indicate which among a set of methods performs best in a real-world dataset. Plasmode simulation combines data resampled from a real-world dataset with synthetic data to generate a known truth for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11740","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/2504.11740/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":"2504.11740","created_at":"2026-07-05T10:49:56.720294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11740v1","created_at":"2026-07-05T10:49:56.720294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11740","created_at":"2026-07-05T10:49:56.720294+00:00"},{"alias_kind":"pith_short_12","alias_value":"PH42EG76P53A","created_at":"2026-07-05T10:49:56.720294+00:00"},{"alias_kind":"pith_short_16","alias_value":"PH42EG76P53ADKQL","created_at":"2026-07-05T10:49:56.720294+00:00"},{"alias_kind":"pith_short_8","alias_value":"PH42EG76","created_at":"2026-07-05T10:49:56.720294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07065","citing_title":"Which Regularized Propensity-Score and Doubly Robust Methods Are Best Calibrated When Exposures or Outcomes Are Rare? A Plasmode Study of Proxy-Based Confounding Adjustment","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK","json":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK.json","graph_json":"https://pith.science/api/pith-number/PH42EG76P53ADKQLQIRNXSXGTK/graph.json","events_json":"https://pith.science/api/pith-number/PH42EG76P53ADKQLQIRNXSXGTK/events.json","paper":"https://pith.science/paper/PH42EG76"},"agent_actions":{"view_html":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK","download_json":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK.json","view_paper":"https://pith.science/paper/PH42EG76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11740&json=true","fetch_graph":"https://pith.science/api/pith-number/PH42EG76P53ADKQLQIRNXSXGTK/graph.json","fetch_events":"https://pith.science/api/pith-number/PH42EG76P53ADKQLQIRNXSXGTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK/action/storage_attestation","attest_author":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK/action/author_attestation","sign_citation":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK/action/citation_signature","submit_replication":"https://pith.science/pith/PH42EG76P53ADKQLQIRNXSXGTK/action/replication_record"}},"created_at":"2026-07-05T10:49:56.720294+00:00","updated_at":"2026-07-05T10:49:56.720294+00:00"}