{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ARSH5QVSEYH667Z7C37YXAHKWF","short_pith_number":"pith:ARSH5QVS","schema_version":"1.0","canonical_sha256":"04647ec2b2260fef7f3f16ff8b80eab17b7439acf4e6d7a7cc615adfa6fc82be","source":{"kind":"arxiv","id":"2309.02244","version":3},"attestation_state":"computed","paper":{"title":"Augmenting Chest X-ray Datasets with Non-Expert Annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amelia Jim\\'enez-S\\'anchez, Cathrine Damgaard, Dovile Juodelyte, Trine Naja Eriksen, Veronika Cheplygina","submitted_at":"2023-09-05T13:52:43Z","abstract_excerpt":"The advancement of machine learning algorithms in medical image analysis requires the expansion of training datasets. A popular and cost-effective approach is automated annotation extraction from free-text medical reports, primarily due to the high costs associated with expert clinicians annotating medical images, such as chest X-rays. However, it has been shown that the resulting datasets are susceptible to biases and shortcuts. Another strategy to increase the size of a dataset is crowdsourcing, a widely adopted practice in general computer vision with some success in medical image analysis."},"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":"2309.02244","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T13:52:43Z","cross_cats_sorted":[],"title_canon_sha256":"8f6dc51d50d837000c31bfc9aff426f8227f628430f279a3470639572d31e7c1","abstract_canon_sha256":"640724ebddd5da14aafa6ce0cf57546775e5b79fddd93e128c6c93dac35f74d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:37.705716Z","signature_b64":"8cDlIvsDT5c4BwvUxKkXLQNS9N5YrzYmdCaKuyh1qVWZWC0gLqYHifhk58i6Lb90jYw8CDte2XJs+x3cbjmrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04647ec2b2260fef7f3f16ff8b80eab17b7439acf4e6d7a7cc615adfa6fc82be","last_reissued_at":"2026-07-05T11:39:37.705124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:37.705124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting Chest X-ray Datasets with Non-Expert Annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amelia Jim\\'enez-S\\'anchez, Cathrine Damgaard, Dovile Juodelyte, Trine Naja Eriksen, Veronika Cheplygina","submitted_at":"2023-09-05T13:52:43Z","abstract_excerpt":"The advancement of machine learning algorithms in medical image analysis requires the expansion of training datasets. A popular and cost-effective approach is automated annotation extraction from free-text medical reports, primarily due to the high costs associated with expert clinicians annotating medical images, such as chest X-rays. However, it has been shown that the resulting datasets are susceptible to biases and shortcuts. Another strategy to increase the size of a dataset is crowdsourcing, a widely adopted practice in general computer vision with some success in medical image analysis."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02244","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/2309.02244/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":"2309.02244","created_at":"2026-07-05T11:39:37.705192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02244v3","created_at":"2026-07-05T11:39:37.705192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02244","created_at":"2026-07-05T11:39:37.705192+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARSH5QVSEYH6","created_at":"2026-07-05T11:39:37.705192+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARSH5QVSEYH667Z7","created_at":"2026-07-05T11:39:37.705192+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARSH5QVS","created_at":"2026-07-05T11:39:37.705192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21291","citing_title":"Fairness and Robustness of CLIP-Based Models for Chest X-rays","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF","json":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF.json","graph_json":"https://pith.science/api/pith-number/ARSH5QVSEYH667Z7C37YXAHKWF/graph.json","events_json":"https://pith.science/api/pith-number/ARSH5QVSEYH667Z7C37YXAHKWF/events.json","paper":"https://pith.science/paper/ARSH5QVS"},"agent_actions":{"view_html":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF","download_json":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF.json","view_paper":"https://pith.science/paper/ARSH5QVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02244&json=true","fetch_graph":"https://pith.science/api/pith-number/ARSH5QVSEYH667Z7C37YXAHKWF/graph.json","fetch_events":"https://pith.science/api/pith-number/ARSH5QVSEYH667Z7C37YXAHKWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF/action/storage_attestation","attest_author":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF/action/author_attestation","sign_citation":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF/action/citation_signature","submit_replication":"https://pith.science/pith/ARSH5QVSEYH667Z7C37YXAHKWF/action/replication_record"}},"created_at":"2026-07-05T11:39:37.705192+00:00","updated_at":"2026-07-05T11:39:37.705192+00:00"}