{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7P7I3OCEZDNV5XXVFRGBJP7I2J","short_pith_number":"pith:7P7I3OCE","schema_version":"1.0","canonical_sha256":"fbfe8db844c8db5edef52c4c14bfe8d2722356a3badc0bee40e7b13c902a031c","source":{"kind":"arxiv","id":"2008.11572","version":1},"attestation_state":"computed","paper":{"title":"On the Composition and Limitations of Publicly Available COVID-19 X-Ray Imaging Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Andreas Dominik Husch, Beatriz Garcia Santa Cruz, Jan S\\\"olter, Matias Nicolas Bossa","submitted_at":"2020-08-26T14:16:01Z","abstract_excerpt":"Machine learning based methods for diagnosis and progression prediction of COVID-19 from imaging data have gained significant attention in the last months, in particular by the use of deep learning models. In this context hundreds of models where proposed with the majority of them trained on public datasets. Data scarcity, mismatch between training and target population, group imbalance, and lack of documentation are important sources of bias, hindering the applicability of these models to real-world clinical practice. Considering that datasets are an essential part of model building and evalu"},"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":"2008.11572","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2020-08-26T14:16:01Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"f54fdd679d381ae28fabe8829da427f5c87029ab83b9490d60ec6cadd34c7d0d","abstract_canon_sha256":"36f8e01dc5254f11fad1283798acc04088fccb666d304abb26bb5fce4aa1a9a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:30:46.342746Z","signature_b64":"gcr+itI9AP7pui0SHi/jltLYczXQQEAnQm+sxZvcqa4WwWxPSMt3vW+rx4swvMfnUOYjC6d3nnR/Rw5XS6znDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbfe8db844c8db5edef52c4c14bfe8d2722356a3badc0bee40e7b13c902a031c","last_reissued_at":"2026-07-05T01:30:46.342302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:30:46.342302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Composition and Limitations of Publicly Available COVID-19 X-Ray Imaging Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Andreas Dominik Husch, Beatriz Garcia Santa Cruz, Jan S\\\"olter, Matias Nicolas Bossa","submitted_at":"2020-08-26T14:16:01Z","abstract_excerpt":"Machine learning based methods for diagnosis and progression prediction of COVID-19 from imaging data have gained significant attention in the last months, in particular by the use of deep learning models. In this context hundreds of models where proposed with the majority of them trained on public datasets. Data scarcity, mismatch between training and target population, group imbalance, and lack of documentation are important sources of bias, hindering the applicability of these models to real-world clinical practice. Considering that datasets are an essential part of model building and evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.11572","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/2008.11572/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":"2008.11572","created_at":"2026-07-05T01:30:46.342372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.11572v1","created_at":"2026-07-05T01:30:46.342372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.11572","created_at":"2026-07-05T01:30:46.342372+00:00"},{"alias_kind":"pith_short_12","alias_value":"7P7I3OCEZDNV","created_at":"2026-07-05T01:30:46.342372+00:00"},{"alias_kind":"pith_short_16","alias_value":"7P7I3OCEZDNV5XXV","created_at":"2026-07-05T01:30:46.342372+00:00"},{"alias_kind":"pith_short_8","alias_value":"7P7I3OCE","created_at":"2026-07-05T01:30:46.342372+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J","json":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J.json","graph_json":"https://pith.science/api/pith-number/7P7I3OCEZDNV5XXVFRGBJP7I2J/graph.json","events_json":"https://pith.science/api/pith-number/7P7I3OCEZDNV5XXVFRGBJP7I2J/events.json","paper":"https://pith.science/paper/7P7I3OCE"},"agent_actions":{"view_html":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J","download_json":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J.json","view_paper":"https://pith.science/paper/7P7I3OCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.11572&json=true","fetch_graph":"https://pith.science/api/pith-number/7P7I3OCEZDNV5XXVFRGBJP7I2J/graph.json","fetch_events":"https://pith.science/api/pith-number/7P7I3OCEZDNV5XXVFRGBJP7I2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J/action/storage_attestation","attest_author":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J/action/author_attestation","sign_citation":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J/action/citation_signature","submit_replication":"https://pith.science/pith/7P7I3OCEZDNV5XXVFRGBJP7I2J/action/replication_record"}},"created_at":"2026-07-05T01:30:46.342372+00:00","updated_at":"2026-07-05T01:30:46.342372+00:00"}