{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UDYO4JYCQULZAXRAMQBANRDDE4","short_pith_number":"pith:UDYO4JYC","canonical_record":{"source":{"id":"2209.09188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T22:30:14Z","cross_cats_sorted":[],"title_canon_sha256":"b34f27bd3a7d14494573146191562a2ae9b3d5f1962f38f09c3ada94c6da1a6d","abstract_canon_sha256":"1f24843fdfbe21c0336232f7ef6e0bbe12c425657ff1a7406be695108eb107a6"},"schema_version":"1.0"},"canonical_sha256":"a0f0ee27028517905e20640206c463271d0314d7770d3233a5c53564c6b089af","source":{"kind":"arxiv","id":"2209.09188","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.09188","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"arxiv_version","alias_value":"2209.09188v1","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09188","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"pith_short_12","alias_value":"UDYO4JYCQULZ","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"pith_short_16","alias_value":"UDYO4JYCQULZAXRA","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"pith_short_8","alias_value":"UDYO4JYC","created_at":"2026-07-05T04:58:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UDYO4JYCQULZAXRAMQBANRDDE4","target":"record","payload":{"canonical_record":{"source":{"id":"2209.09188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T22:30:14Z","cross_cats_sorted":[],"title_canon_sha256":"b34f27bd3a7d14494573146191562a2ae9b3d5f1962f38f09c3ada94c6da1a6d","abstract_canon_sha256":"1f24843fdfbe21c0336232f7ef6e0bbe12c425657ff1a7406be695108eb107a6"},"schema_version":"1.0"},"canonical_sha256":"a0f0ee27028517905e20640206c463271d0314d7770d3233a5c53564c6b089af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:50.441860Z","signature_b64":"LWYB7LJLogZrBFc0O7+3lfqm7BDNYvtl19exlmc1GIYyIJUVjXE/DPD1NURqzdSX1hcq7g7BXP4Jc0j1Yd8UCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f0ee27028517905e20640206c463271d0314d7770d3233a5c53564c6b089af","last_reissued_at":"2026-07-05T04:58:50.441456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:50.441456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.09188","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:58:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"922Y6twuDA6jg+goAw5Z1Whh88qYTraEy3vB3ceUo+1BHHfu8t5FpmfepTZSw8dDDdqbldXk1noRgTpDwyajAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:20:04.122890Z"},"content_sha256":"402bc1b500278c625d1f72b3448b13734a1c066a49e26defe4f9fe0131d187ce","schema_version":"1.0","event_id":"sha256:402bc1b500278c625d1f72b3448b13734a1c066a49e26defe4f9fe0131d187ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UDYO4JYCQULZAXRAMQBANRDDE4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Avoiding Biased Clinical Machine Learning Model Performance Estimates in the Presence of Label Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Conor K. Corbin, Jonathan H. Chen, Michael Baiocchi","submitted_at":"2022-09-15T22:30:14Z","abstract_excerpt":"When evaluating the performance of clinical machine learning models, one must consider the deployment population. When the population of patients with observed labels is only a subset of the deployment population (label selection), standard model performance estimates on the observed population may be misleading. In this study we describe three classes of label selection and simulate five causally distinct scenarios to assess how particular selection mechanisms bias a suite of commonly reported binary machine learning model performance metrics. Simulations reveal that when selection is affecte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09188","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/2209.09188/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":"2026-07-05T04:58:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKarikUKSw/Ee2FywwFLfqnbHjnPa2OiBwhrsXfjyVlwAb4rgXdquNzvkto1dvquJpS00QMDQ5yzxjwlQShSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:20:04.123256Z"},"content_sha256":"461aee771f696b0cd14a0e48b1db257e2223a98296814448a56172977b9f536a","schema_version":"1.0","event_id":"sha256:461aee771f696b0cd14a0e48b1db257e2223a98296814448a56172977b9f536a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDYO4JYCQULZAXRAMQBANRDDE4/bundle.json","state_url":"https://pith.science/pith/UDYO4JYCQULZAXRAMQBANRDDE4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDYO4JYCQULZAXRAMQBANRDDE4/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":"2026-07-06T23:20:04Z","links":{"resolver":"https://pith.science/pith/UDYO4JYCQULZAXRAMQBANRDDE4","bundle":"https://pith.science/pith/UDYO4JYCQULZAXRAMQBANRDDE4/bundle.json","state":"https://pith.science/pith/UDYO4JYCQULZAXRAMQBANRDDE4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDYO4JYCQULZAXRAMQBANRDDE4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UDYO4JYCQULZAXRAMQBANRDDE4","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":"1f24843fdfbe21c0336232f7ef6e0bbe12c425657ff1a7406be695108eb107a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T22:30:14Z","title_canon_sha256":"b34f27bd3a7d14494573146191562a2ae9b3d5f1962f38f09c3ada94c6da1a6d"},"schema_version":"1.0","source":{"id":"2209.09188","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.09188","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"arxiv_version","alias_value":"2209.09188v1","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09188","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"pith_short_12","alias_value":"UDYO4JYCQULZ","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"pith_short_16","alias_value":"UDYO4JYCQULZAXRA","created_at":"2026-07-05T04:58:50Z"},{"alias_kind":"pith_short_8","alias_value":"UDYO4JYC","created_at":"2026-07-05T04:58:50Z"}],"graph_snapshots":[{"event_id":"sha256:461aee771f696b0cd14a0e48b1db257e2223a98296814448a56172977b9f536a","target":"graph","created_at":"2026-07-05T04:58:50Z","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/2209.09188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When evaluating the performance of clinical machine learning models, one must consider the deployment population. When the population of patients with observed labels is only a subset of the deployment population (label selection), standard model performance estimates on the observed population may be misleading. In this study we describe three classes of label selection and simulate five causally distinct scenarios to assess how particular selection mechanisms bias a suite of commonly reported binary machine learning model performance metrics. Simulations reveal that when selection is affecte","authors_text":"Conor K. Corbin, Jonathan H. Chen, Michael Baiocchi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T22:30:14Z","title":"Avoiding Biased Clinical Machine Learning Model Performance Estimates in the Presence of Label Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09188","kind":"arxiv","version":1},"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":"sha256:402bc1b500278c625d1f72b3448b13734a1c066a49e26defe4f9fe0131d187ce","target":"record","created_at":"2026-07-05T04:58:50Z","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":"1f24843fdfbe21c0336232f7ef6e0bbe12c425657ff1a7406be695108eb107a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T22:30:14Z","title_canon_sha256":"b34f27bd3a7d14494573146191562a2ae9b3d5f1962f38f09c3ada94c6da1a6d"},"schema_version":"1.0","source":{"id":"2209.09188","kind":"arxiv","version":1}},"canonical_sha256":"a0f0ee27028517905e20640206c463271d0314d7770d3233a5c53564c6b089af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0f0ee27028517905e20640206c463271d0314d7770d3233a5c53564c6b089af","first_computed_at":"2026-07-05T04:58:50.441456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:50.441456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LWYB7LJLogZrBFc0O7+3lfqm7BDNYvtl19exlmc1GIYyIJUVjXE/DPD1NURqzdSX1hcq7g7BXP4Jc0j1Yd8UCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:50.441860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.09188","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:402bc1b500278c625d1f72b3448b13734a1c066a49e26defe4f9fe0131d187ce","sha256:461aee771f696b0cd14a0e48b1db257e2223a98296814448a56172977b9f536a"],"state_sha256":"6a2905cb66d939eabe9ef05403940b04e6075006f15c57e4b74c51f481500078"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XRUIzVrwEZK8eleb+LhOsnzHq5O4o+bqHSeYqbuhmjnXncHfPVC+G+2HVknp8c2IEqCF7RUmupMjFEuHQYddAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:20:04.125089Z","bundle_sha256":"d9d26b5bb11e03ccaa3e7b5b85f5e82a2841aa2fd4a041da55e0c8b22bc6a50e"}}