{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PUU4R7QSJ7LXUBNON52RRWX4TH","short_pith_number":"pith:PUU4R7QS","schema_version":"1.0","canonical_sha256":"7d29c8fe124fd77a05ae6f7518dafc99d9b938647c1c40cb40b475f015c298cf","source":{"kind":"arxiv","id":"2210.17398","version":3},"attestation_state":"computed","paper":{"title":"Rethinking Generalization: The Impact of Annotation Style on Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Brennan Nichyporuk, Douglas L. Arnold, Jean-Pierre R. Falet, Jillian Cardinell, Justin Szeto, Raghav Mehta, Sotirios A. Tsaftaris, Tal Arbel","submitted_at":"2022-10-31T15:28:49Z","abstract_excerpt":"Generalization is an important attribute of machine learning models, particularly for those that are to be deployed in a medical context, where unreliable predictions can have real world consequences. While the failure of models to generalize across datasets is typically attributed to a mismatch in the data distributions, performance gaps are often a consequence of biases in the 'ground-truth' label annotations. This is particularly important in the context of medical image segmentation of pathological structures (e.g. lesions), where the annotation process is much more subjective, and affecte"},"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":"2210.17398","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-31T15:28:49Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"d7a04eec31f907dade4aa85b858c5ac2c896024e6c17e7bd817cbe5a4bd61d68","abstract_canon_sha256":"e168bb5b613ae2a05d799dbbf4da5bec3dc468f571ec327af1903cf9c85d9573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:44.558389Z","signature_b64":"rxq/qTazIVARXqhliVTom36E7AxOhXCegaSt2rvDTQL74qC5+eTRLsZ/UxtRoHMi2hmtHDDirwhsjTqCp4twCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d29c8fe124fd77a05ae6f7518dafc99d9b938647c1c40cb40b475f015c298cf","last_reissued_at":"2026-07-05T05:24:44.557898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:44.557898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Generalization: The Impact of Annotation Style on Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Brennan Nichyporuk, Douglas L. Arnold, Jean-Pierre R. Falet, Jillian Cardinell, Justin Szeto, Raghav Mehta, Sotirios A. Tsaftaris, Tal Arbel","submitted_at":"2022-10-31T15:28:49Z","abstract_excerpt":"Generalization is an important attribute of machine learning models, particularly for those that are to be deployed in a medical context, where unreliable predictions can have real world consequences. While the failure of models to generalize across datasets is typically attributed to a mismatch in the data distributions, performance gaps are often a consequence of biases in the 'ground-truth' label annotations. This is particularly important in the context of medical image segmentation of pathological structures (e.g. lesions), where the annotation process is much more subjective, and affecte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17398","kind":"arxiv","version":3},"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/2210.17398/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":"2210.17398","created_at":"2026-07-05T05:24:44.557958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17398v3","created_at":"2026-07-05T05:24:44.557958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17398","created_at":"2026-07-05T05:24:44.557958+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUU4R7QSJ7LX","created_at":"2026-07-05T05:24:44.557958+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUU4R7QSJ7LXUBNO","created_at":"2026-07-05T05:24:44.557958+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUU4R7QS","created_at":"2026-07-05T05:24:44.557958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04563","citing_title":"Temporal Inversion for Learning Interval Change in Chest X-Rays","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH","json":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH.json","graph_json":"https://pith.science/api/pith-number/PUU4R7QSJ7LXUBNON52RRWX4TH/graph.json","events_json":"https://pith.science/api/pith-number/PUU4R7QSJ7LXUBNON52RRWX4TH/events.json","paper":"https://pith.science/paper/PUU4R7QS"},"agent_actions":{"view_html":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH","download_json":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH.json","view_paper":"https://pith.science/paper/PUU4R7QS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17398&json=true","fetch_graph":"https://pith.science/api/pith-number/PUU4R7QSJ7LXUBNON52RRWX4TH/graph.json","fetch_events":"https://pith.science/api/pith-number/PUU4R7QSJ7LXUBNON52RRWX4TH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH/action/storage_attestation","attest_author":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH/action/author_attestation","sign_citation":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH/action/citation_signature","submit_replication":"https://pith.science/pith/PUU4R7QSJ7LXUBNON52RRWX4TH/action/replication_record"}},"created_at":"2026-07-05T05:24:44.557958+00:00","updated_at":"2026-07-05T05:24:44.557958+00:00"}