{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4ANRVNI4BBN3LTQWP3NBLACUGX","short_pith_number":"pith:4ANRVNI4","schema_version":"1.0","canonical_sha256":"e01b1ab51c085bb5ce167eda15805435e382fff9da1ae1e10f2b283922f61331","source":{"kind":"arxiv","id":"1909.01940","version":2},"attestation_state":"computed","paper":{"title":"Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","stat.ML"],"primary_cat":"eess.IV","authors_text":"Eduardo H. P. Pooch, Pedro L. Ballester, Rodrigo C. Barros","submitted_at":"2019-09-03T14:03:55Z","abstract_excerpt":"While deep learning models become more widespread, their ability to handle unseen data and generalize for any scenario is yet to be challenged. In medical imaging, there is a high heterogeneity of distributions among images based on the equipment that generates them and their parametrization. This heterogeneity triggers a common issue in machine learning called domain shift, which represents the difference between the training data distribution and the distribution of where a model is employed. A high domain shift tends to implicate in a poor generalization performance from the models. In this"},"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":"1909.01940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-09-03T14:03:55Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"44e135037a1ab72e389737dc92598c4884043773522ebbdc204512fb1a269560","abstract_canon_sha256":"836c40b8bb06cbd4acc5f047fe087245c07c7a36ee7ae29b404ac6b797dff961"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:03.052241Z","signature_b64":"cz1ua4bz5+qw9BGpZ3BboRC0v2eIfKky68ozWqAjkBX5hXS3CxixzdDRTOg4y2gdtiaBZad1IXY7bZrisaEbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e01b1ab51c085bb5ce167eda15805435e382fff9da1ae1e10f2b283922f61331","last_reissued_at":"2026-07-05T10:56:03.051737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:03.051737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","stat.ML"],"primary_cat":"eess.IV","authors_text":"Eduardo H. P. Pooch, Pedro L. Ballester, Rodrigo C. Barros","submitted_at":"2019-09-03T14:03:55Z","abstract_excerpt":"While deep learning models become more widespread, their ability to handle unseen data and generalize for any scenario is yet to be challenged. In medical imaging, there is a high heterogeneity of distributions among images based on the equipment that generates them and their parametrization. This heterogeneity triggers a common issue in machine learning called domain shift, which represents the difference between the training data distribution and the distribution of where a model is employed. A high domain shift tends to implicate in a poor generalization performance from the models. In this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01940","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/1909.01940/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":"1909.01940","created_at":"2026-07-05T10:56:03.051791+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01940v2","created_at":"2026-07-05T10:56:03.051791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01940","created_at":"2026-07-05T10:56:03.051791+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ANRVNI4BBN3","created_at":"2026-07-05T10:56:03.051791+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ANRVNI4BBN3LTQW","created_at":"2026-07-05T10:56:03.051791+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ANRVNI4","created_at":"2026-07-05T10:56:03.051791+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/4ANRVNI4BBN3LTQWP3NBLACUGX","json":"https://pith.science/pith/4ANRVNI4BBN3LTQWP3NBLACUGX.json","graph_json":"https://pith.science/api/pith-number/4ANRVNI4BBN3LTQWP3NBLACUGX/graph.json","events_json":"https://pith.science/api/pith-number/4ANRVNI4BBN3LTQWP3NBLACUGX/events.json","paper":"https://pith.science/paper/4ANRVNI4"},"agent_actions":{"view_html":"https://pith.science/pith/4ANRVNI4BBN3LTQWP3NBLACUGX","download_json":"https://pith.science/pith/4ANRVNI4BBN3LTQWP3NBLACUGX.json","view_paper":"https://pith.science/paper/4ANRVNI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01940&json=true","fetch_graph":"https://pith.science/api/pith-number/4ANRVNI4BBN3LTQWP3NBLACUGX/graph.json","fetch_events":"https://pith.science/api/pith-number/4ANRVNI4BBN3LTQWP3NBLACUGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ANRVNI4BBN3LTQWP3NBLACUGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ANRVNI4BBN3LTQWP3NBLACUGX/action/storage_attestation","attest_author":"https://pith.science/pith/4ANRVNI4BBN3LTQWP3NBLACUGX/action/author_attestation","sign_citation":"https://pith.science/pith/4ANRVNI4BBN3LTQWP3NBLACUGX/action/citation_signature","submit_replication":"https://pith.science/pith/4ANRVNI4BBN3LTQWP3NBLACUGX/action/replication_record"}},"created_at":"2026-07-05T10:56:03.051791+00:00","updated_at":"2026-07-05T10:56:03.051791+00:00"}