{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5DN7EO3EM4GITIVNWV3445F53B","short_pith_number":"pith:5DN7EO3E","canonical_record":{"source":{"id":"2107.09730","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2021-07-20T19:01:24Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"53649913b94919713f2979ae87c983d3498736b86248279a70f3cd94a6858c06","abstract_canon_sha256":"fc8eb42606a67e42eb3dc6d6cd21d3d5b3fbfc13e05830b6bf88facec51029a2"},"schema_version":"1.0"},"canonical_sha256":"e8dbf23b64670c89a2adb577ce74bdd8527b0736ad338218e21e9cc3a5aa42b2","source":{"kind":"arxiv","id":"2107.09730","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09730","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09730v2","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09730","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"5DN7EO3EM4GI","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"5DN7EO3EM4GITIVN","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"5DN7EO3E","created_at":"2026-07-05T04:14:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5DN7EO3EM4GITIVNWV3445F53B","target":"record","payload":{"canonical_record":{"source":{"id":"2107.09730","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2021-07-20T19:01:24Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"53649913b94919713f2979ae87c983d3498736b86248279a70f3cd94a6858c06","abstract_canon_sha256":"fc8eb42606a67e42eb3dc6d6cd21d3d5b3fbfc13e05830b6bf88facec51029a2"},"schema_version":"1.0"},"canonical_sha256":"e8dbf23b64670c89a2adb577ce74bdd8527b0736ad338218e21e9cc3a5aa42b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:24.609123Z","signature_b64":"U4Vy3GPETsiJYDQ1V5A6a90+oJ/jdCuE1YeiZPgT3ZlqUHEkFNXq4LvWkt21zJR1T8gyzsPNvsfY+ZO60f6aBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8dbf23b64670c89a2adb577ce74bdd8527b0736ad338218e21e9cc3a5aa42b2","last_reissued_at":"2026-07-05T04:14:24.608646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:24.608646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.09730","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dDho9cGjOdnQNAp7S3/PNQLFTbd4xOsj0bFB+CadHGrQTZ+1E/GCP1pZ0E2jm+LzHbsqqV5BEUcrq0gSqFUMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T12:49:23.815136Z"},"content_sha256":"1ddfe854f65ce8345a30e27ba810ea61f9b835a4a7b32f4d6db9742b199d5e51","schema_version":"1.0","event_id":"sha256:1ddfe854f65ce8345a30e27ba810ea61f9b835a4a7b32f4d6db9742b199d5e51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5DN7EO3EM4GITIVNWV3445F53B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A flexible approach for variable selection in large-scale healthcare database studies with missing covariate and outcome data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ME","authors_text":"Chuyue Huang, Jung-Yi Joyce Lin, Liangyuan Hu, Steven Lawrence, Usha Govindarajulu","submitted_at":"2021-07-20T19:01:24Z","abstract_excerpt":"Prior work has shown that combining bootstrap imputation with tree-based machine learning variable selection methods can provide good performances achievable on fully observed data when covariate and outcome data are missing at random (MAR). This approach however is computationally expensive, especially on large-scale datasets. We propose an inference-based method, called RR-BART, which leverages the likelihood-based Bayesian machine learning technique, Bayesian additive regression trees, and uses Rubin's rule to combine the estimates and variances of the variable importance measures on multip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09730","kind":"arxiv","version":2},"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/2107.09730/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"61EPrkdWkmNRdWrrYZ/FXMGKhkxxCFUz+N0drBrkU/sFIpx7y7zilu+sxboh+AAAea8ZnBoa2Lkm9LK04aK8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T12:49:23.815558Z"},"content_sha256":"429664eb176762da9dbaffbabab82f0f7465cdf8e1695744743cad5705df60b2","schema_version":"1.0","event_id":"sha256:429664eb176762da9dbaffbabab82f0f7465cdf8e1695744743cad5705df60b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DN7EO3EM4GITIVNWV3445F53B/bundle.json","state_url":"https://pith.science/pith/5DN7EO3EM4GITIVNWV3445F53B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DN7EO3EM4GITIVNWV3445F53B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-13T12:49:23Z","links":{"resolver":"https://pith.science/pith/5DN7EO3EM4GITIVNWV3445F53B","bundle":"https://pith.science/pith/5DN7EO3EM4GITIVNWV3445F53B/bundle.json","state":"https://pith.science/pith/5DN7EO3EM4GITIVNWV3445F53B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DN7EO3EM4GITIVNWV3445F53B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5DN7EO3EM4GITIVNWV3445F53B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fc8eb42606a67e42eb3dc6d6cd21d3d5b3fbfc13e05830b6bf88facec51029a2","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2021-07-20T19:01:24Z","title_canon_sha256":"53649913b94919713f2979ae87c983d3498736b86248279a70f3cd94a6858c06"},"schema_version":"1.0","source":{"id":"2107.09730","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09730","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09730v2","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09730","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"5DN7EO3EM4GI","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"5DN7EO3EM4GITIVN","created_at":"2026-07-05T04:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"5DN7EO3E","created_at":"2026-07-05T04:14:24Z"}],"graph_snapshots":[{"event_id":"sha256:429664eb176762da9dbaffbabab82f0f7465cdf8e1695744743cad5705df60b2","target":"graph","created_at":"2026-07-05T04:14:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.09730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior work has shown that combining bootstrap imputation with tree-based machine learning variable selection methods can provide good performances achievable on fully observed data when covariate and outcome data are missing at random (MAR). This approach however is computationally expensive, especially on large-scale datasets. We propose an inference-based method, called RR-BART, which leverages the likelihood-based Bayesian machine learning technique, Bayesian additive regression trees, and uses Rubin's rule to combine the estimates and variances of the variable importance measures on multip","authors_text":"Chuyue Huang, Jung-Yi Joyce Lin, Liangyuan Hu, Steven Lawrence, Usha Govindarajulu","cross_cats":["stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2021-07-20T19:01:24Z","title":"A flexible approach for variable selection in large-scale healthcare database studies with missing covariate and outcome data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09730","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1ddfe854f65ce8345a30e27ba810ea61f9b835a4a7b32f4d6db9742b199d5e51","target":"record","created_at":"2026-07-05T04:14:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fc8eb42606a67e42eb3dc6d6cd21d3d5b3fbfc13e05830b6bf88facec51029a2","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2021-07-20T19:01:24Z","title_canon_sha256":"53649913b94919713f2979ae87c983d3498736b86248279a70f3cd94a6858c06"},"schema_version":"1.0","source":{"id":"2107.09730","kind":"arxiv","version":2}},"canonical_sha256":"e8dbf23b64670c89a2adb577ce74bdd8527b0736ad338218e21e9cc3a5aa42b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8dbf23b64670c89a2adb577ce74bdd8527b0736ad338218e21e9cc3a5aa42b2","first_computed_at":"2026-07-05T04:14:24.608646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:24.608646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U4Vy3GPETsiJYDQ1V5A6a90+oJ/jdCuE1YeiZPgT3ZlqUHEkFNXq4LvWkt21zJR1T8gyzsPNvsfY+ZO60f6aBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:24.609123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.09730","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ddfe854f65ce8345a30e27ba810ea61f9b835a4a7b32f4d6db9742b199d5e51","sha256:429664eb176762da9dbaffbabab82f0f7465cdf8e1695744743cad5705df60b2"],"state_sha256":"4704d2a3cd22667b1afa5a9a527f18f707d0b2659909ee8aaf15c7f162e236ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RQDetwR9jMw3wnbOkP0Zq3zQ+QmZNEvyw7G5Ay7ZF+Xij/diyjKv4n9hvoL/GWitL2gzQrycNzid6Y7o0xaxBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T12:49:23.818151Z","bundle_sha256":"0ef86a98a8bc485d5b3ffd5adf7cae5114f7129b89b871001369661ec5720bc2"}}