{"as_of":"2026-08-12T23:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2ed8e153c74003d8793de55feb55c15c570d766a62e2631fce4d80fa07d7ab88","coverage":[{"denominator":66,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":66,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T21:53:45.886010Z","state":"measured"},{"denominator":66,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":66,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.04030/citation-record","integrity":"/paper/2412.04030/integrity","json":"/paper/2412.04030/citation-record.json","paper":"/paper/2412.04030"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.455738Z","title":"Characterizing the clinical adoption of medical ai devices through u.s","venue":null,"work_id":"633111af-9ed7-4e31-b249-473bb1ae9b31","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.704173Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:90ee4ac4b3435438a6210f841b99024fbea986ec6b5062e204dbdf8b49ad0acf","observation_id":"545ad308-9221-4ced-8ea9-7d32b6cb90d6","resolution":{"observed_at":"2026-08-11T21:53:46.458288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.447064Z","title":"Artificial intelligence versus clinicians in disease diagnosis: systematic review.JMIR medical informatics, 7(3):e10010, 2019","venue":null,"work_id":"0b177097-5da4-4a33-9962-4e93d3922279","year":2019},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.708029Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:c38947c9e29ffbb3c4d1006b8df57b471a3e2ff7ce353f7b52cc9ccd4e9cedb0","observation_id":"29c39b9f-98b0-4e3f-b9ef-a8f265601f5b","resolution":{"observed_at":"2026-08-11T21:53:46.449617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.440750Z","title":"Autonomous chest radiograph reporting using ai: estimation of clinical impact","venue":null,"work_id":"c23536a1-5103-47c2-8962-f5bcb4d706ff","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.711062Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:0a374d47bab1f583ba509d6fb49f65b60a21955dd6da2eb60dfd9e9e64d1a257","observation_id":"ba9eef18-3d16-452c-b16d-10e845aab2d9","resolution":{"observed_at":"2026-08-11T21:53:46.443226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.433508Z","title":"Ho, and James Zou","venue":null,"work_id":"8174765e-6265-4bf2-900f-9a02ccc08b03","year":2021},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.713981Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:db676f35da8a7fe3cac41e8324cd0ff2086b055cc81d2bd46e2ba4980bfb656e","observation_id":"ec6666b9-5d40-4000-bab7-0418f351457a","resolution":{"observed_at":"2026-08-11T21:53:46.435781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.426478Z","title":"Detecting shortcuts in medical images-a case study in chest x-rays","venue":null,"work_id":"67709002-a0fa-4f99-8716-154eb37f40ea","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.716186Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:1387b1e136e6d7b25d2d0b790b845b4663b7ed02385e7e87cf07967ad72d9a42","observation_id":"6187929e-c675-4736-9e41-f16b5b96e7fe","resolution":{"observed_at":"2026-08-11T21:53:46.429117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.416602Z","title":"Hidden stratification causes clinically meaningful failures in machine learning for medical imaging","venue":null,"work_id":"135871cd-6ca0-47d8-ad96-c78b1657b76e","year":2020},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.718274Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:0ae479c393333f11e16818ca03e8ff8bacd2cda36dfc297d64cffafd32ee38ca","observation_id":"98b6e9c1-03b1-480b-971a-a49f570d6a3a","resolution":{"observed_at":"2026-08-11T21:53:46.420375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.406863Z","title":"Counterfactual contrastive learning: robust representations via causal image synthesis","venue":null,"work_id":"05a559da-9abe-4b00-863a-1d3e2f4130dc","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.721958Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:189e19f6bb4d75ff226c0d949cea00c5917293c8527e42b352926146653f39a3","observation_id":"1b6da36e-01dc-46f1-8d95-a2a591c01a5a","resolution":{"observed_at":"2026-08-11T21:53:46.409921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.399188Z","title":"All you need is a guiding hand: Mitigating short- cut bias in deep learning models for medical imaging","venue":null,"work_id":"1ab6d80c-eb89-4932-84f0-b261e9392e8d","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.723859Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:892236395fada4214eb855ef943b0edcf9b8702be9f577d4941d8d4a95bd4895","observation_id":"d1e5361e-1f55-44ac-b30f-246e15402168","resolution":{"observed_at":"2026-08-11T21:53:46.402143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.391166Z","title":"Deep learning for understanding multilabel imbalanced chest x-ray datasets","venue":null,"work_id":"60ef29db-1da3-490d-a75c-5f31acd60c54","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.725910Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:46f2037f72ede3037f1ebe92f104844a40c4d80e135682071049ca6aed44307f","observation_id":"4b80b51d-908c-4771-b744-c1480293cdfd","resolution":{"observed_at":"2026-08-11T21:53:46.394234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.382475Z","title":"Airogs: artificial intelligence for robust glaucoma screening chal- lenge","venue":null,"work_id":"871b3ca1-c084-41c4-94a0-45e69b5b0755","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.727697Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:6eec147c713f135dfbae0f1568d1a29362cd1469eda04aad0dc89c8648558059","observation_id":"fc461182-c07b-465e-9638-8800947cb678","resolution":{"observed_at":"2026-08-11T21:53:46.384941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.374883Z","title":"Machine learning and deep learning methods for skin lesion classification and diagnosis: a systematic review.Diagnostics, 11(8):1390, 2021","venue":null,"work_id":"3e8ced14-fffa-4ba6-8501-eba07e2161a8","year":2021},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.730405Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:677599b38bf40fb3250e96ad833c09f061971674106623bc8b9646e001048d3a","observation_id":"68c134c0-4f00-4721-96d8-3cd5bb608c32","resolution":{"observed_at":"2026-08-11T21:53:46.378019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:45.733698Z","title":"Dynamic routing between capsules","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.733698Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:d80670b319780afd3b5be658927c3c077e500b2250f006336063263b6a876c37","observation_id":"c72b7881-e2f4-43ca-80e5-5e16903b41a2","resolution":{"observed_at":"2026-08-11T21:53:45.733698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.365154Z","title":"Capsule networks against medical imaging data challenges","venue":null,"work_id":"1a62a0fc-f829-4535-a9a9-00f5a3b93a2b","year":2018},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.736451Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:202473781e94069c0fe72818836b692c12799f98bec53b89869d3639e4ba7dd4","observation_id":"ae84f1c5-66c6-43e5-9c64-b99efb2633dc","resolution":{"observed_at":"2026-08-11T21:53:46.367603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.358254Z","title":"A capsule network-based for identification of glaucoma in retinal images","venue":null,"work_id":"03fdb73a-80b6-4b82-92cf-38e3fa4d0a38","year":2020},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.739107Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:692f880b3acad6c6c5999efa84d75a3a3f53a3f4c522eb934d3139baccffb63e","observation_id":"72623573-76d4-48aa-b1d5-27426ef2d558","resolution":{"observed_at":"2026-08-11T21:53:46.361073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:45.741720Z","title":"Transformers in medical imaging: A survey.Medical Image Analysis, 88:102802, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.741720Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:76ef6532c9c67d837896dcad23303b87e0744cf91678b371a4c4048c290a156b","observation_id":"68cec960-43c8-448c-8a58-edb8ddaf6f4a","resolution":{"observed_at":"2026-08-11T21:53:45.741720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.345800Z","title":"Lt-vit: A vision transformer for multi-label chest x-ray classification","venue":null,"work_id":"7ed43f5b-e012-4415-b788-9becbb287304","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.744549Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:6839003db4a63396de6f2b664d84eaa7b19f4d4154c8cda9ba3b527d01cdbb4f","observation_id":"5f77afac-7865-420f-9e39-f8a31920e18c","resolution":{"observed_at":"2026-08-11T21:53:46.348640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.337704Z","title":"Detecting glaucoma from fundus photographs using deep learning without convolutions: transformer for improved generalization.Ophthal- mology science, 3(1):100233, 2023","venue":null,"work_id":"29f25232-fa4f-4073-944d-09542b1bbb3a","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.747462Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:90f6c3f42b23dbe358792c3b40dfb63cdf60a7922f3e59d3d63c7a6723e8ceb8","observation_id":"fa7a34cb-ec53-4090-8108-9a60dde14b39","resolution":{"observed_at":"2026-08-11T21:53:46.340809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.01469","last_updated":"2024-05-02T16:59:10Z","snapshot_observed_at":"2026-08-10T21:48:39.958496Z","submitted_at":"2024-05-02T16:59:10Z","title":"Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.01469","snapshot_observed_at":"2026-08-11T21:53:45.750351Z","title":"Advancing human-centric ai for robust x-ray analysis through holistic self-supervised learning.arXiv preprint arXiv:2405.01469, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.750351Z"},"links":{"cited_paper":"/paper/2405.01469","citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:91c1f7c22c0f6b3f970454e9af588854ef0e2d0ea4bd735efc67590bf9f2dd9a","observation_id":"a5a4e858-4071-4810-a460-fe3b2f8734bd","resolution":{"observed_at":"2026-08-11T21:53:45.750351Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.02463","last_updated":"2023-11-16T12:38:46Z","snapshot_observed_at":"2026-08-08T04:57:05.131540Z","submitted_at":"2023-08-04T17:00:38Z","title":"Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.02463","snapshot_observed_at":"2026-08-11T21:53:45.753949Z","title":"Towards generalist foundation model for radiology.arXiv preprint arXiv:2308.02463, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.753949Z"},"links":{"cited_paper":"/paper/2308.02463","citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:cb8db9cfc45b94c7a6414c77d493ea5beb791febf6e38aafa161b1215fb96019","observation_id":"6f08b4e2-3b87-4cb0-b37a-c24bd6ca346e","resolution":{"observed_at":"2026-08-11T21:53:45.753949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.330990Z","title":"Visual–language foundation models in medicine.The Visual Computer, pages 1–20, 2024","venue":null,"work_id":"30bebbd0-2741-4a5b-94ca-69bee25f9fb8","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.757160Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:ef8ac99ac43000ba28704fdbec5da3ff7e88df7372084862fc51c1de2cf11d5e","observation_id":"3a594dd4-f6da-4ecf-8edf-36d396fceabb","resolution":{"observed_at":"2026-08-11T21:53:46.333593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.02865","last_updated":"2025-08-11T18:17:44Z","snapshot_observed_at":"2026-08-12T23:08:06.115585Z","submitted_at":"2024-08-05T23:31:07Z","title":"VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.02865","snapshot_observed_at":"2026-08-11T21:53:45.760258Z","title":"Visionunite: A vision-language foundation model for oph- thalmology enhanced with clinical knowledge","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.760258Z"},"links":{"cited_paper":"/paper/2408.02865","citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:31fa0691fab372fc73fb3622822709b4c2928ec88a831f7bdd7cdd0379593faf","observation_id":"1ab86a22-7071-41dc-9382-a51a20db2517","resolution":{"observed_at":"2026-08-11T21:53:45.760258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.324612Z","title":"Shortcutlearningindeepneural networks","venue":null,"work_id":"543837a4-5438-400d-af15-03d79a268c3e","year":2020},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.764936Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:a467f7ce38f96972413b1339326046ebbc6a193edcd331ec76d067811c79c5c4","observation_id":"7a37a12c-cc83-4db7-a04c-c9298a94cd27","resolution":{"observed_at":"2026-08-11T21:53:46.327060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.317824Z","title":"shortcuts","venue":null,"work_id":"a7c68ce5-27cf-4db5-9ce2-eef2076a2c03","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.767694Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:6811c9d3ef59913e436de7608ba8d6f57d6fd047becf4bea2b43ceca03b008da","observation_id":"e42eefc0-e563-41fc-bf20-9b387b68f112","resolution":{"observed_at":"2026-08-11T21:53:46.320662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.310792Z","title":"Detecting and mitigating the clever hans effect in medical imaging: A scoping review.Journal of Imaging Informatics in Medicine, pages 1–17, 2024","venue":null,"work_id":"9e0035df-c88a-48d4-ace4-7fee7ef06fbc","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.770217Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:cbfe58b3a6c98a5c5534aa006437a135074b38e3e7c5cb1d524b52ed74b683b2","observation_id":"f9f4264a-e481-4cfb-9314-119937a1f837","resolution":{"observed_at":"2026-08-11T21:53:46.313484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.302249Z","title":"An unex- pected confounder: how brain shape can be used to classify mri scans? InMedical Imaging with Deep Learning, 2024","venue":null,"work_id":"a02e9f14-af53-4fc9-8768-e0b8c1d39f9e","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.774251Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:90dc522c67dfbf338b79653a82be61fac703d3724904d04a583e9364e4d2a0cf","observation_id":"afb82f1c-f554-44a2-8a40-20d3ed01bec6","resolution":{"observed_at":"2026-08-11T21:53:46.305091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.295626Z","title":"There are no shortcuts to anywhere worth going: Identifying shortcuts in deep learningmodelsformedicalimageanalysis","venue":null,"work_id":"e497bb00-a1c9-48b5-82a2-c95e313764ac","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.777662Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:dcdf8ae06f8fb263269e1e12e80c6df7b7753cb59595423fb7b4b4fa74ce22a3","observation_id":"a9580497-95a7-44fd-9032-562c6f544a15","resolution":{"observed_at":"2026-08-11T21:53:46.298398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.289205Z","title":"Fast diffusion-based counterfactuals for shortcut removal and generation","venue":null,"work_id":"4d645497-f63e-476d-9ae2-aabb524d5f0d","year":2025},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.781026Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:0fbc88b1562b6463ee8cfdd0b23e8f281c5bb49e1084613407bedfcd523f5679","observation_id":"4621bbda-645a-47a1-b710-2a1cd5104d1c","resolution":{"observed_at":"2026-08-11T21:53:46.291748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.283131Z","title":"Radedit: stress-testing biomedical vision models via diffusion image editing","venue":null,"work_id":"d097994a-b680-4a77-b4e5-a6f622025c97","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.784646Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:e30524370c0cb513ca5772a714d24e64910db86c2f26701cc3da44f68e0c975d","observation_id":"e6c59ad3-274d-4784-a634-14c3800db018","resolution":{"observed_at":"2026-08-11T21:53:46.285315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.277064Z","title":"(de)constructing bias on skin lesion datasets","venue":null,"work_id":"b9faf28c-31aa-4501-b6d3-72e4070c7b57","year":2019},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.787514Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:891761566a0ec6d86a1c26935ec0ede92e6d8872f59a673c31b1bcdc46013db1","observation_id":"6209ce36-ba57-4a63-9ffe-3208d122f7d7","resolution":{"observed_at":"2026-08-11T21:53:46.279586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.269998Z","title":"Deep learning on fundus images detects glau- coma beyond the optic disc.Scientific Reports, 11(1):20313, 2021","venue":null,"work_id":"719c5d06-0cc8-4d04-ac0a-7b378f484924","year":2021},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.791446Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:afa0705881ffd95268a279048baa2ebaf26fed8aa6a72e57476c9744452b5e69","observation_id":"f7a170ff-c0ce-4a79-8457-011e3f7f68f5","resolution":{"observed_at":"2026-08-11T21:53:46.272294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.262390Z","title":"Generalisation chal- lenges in deep learning models for medical imagery: insights from external valida- tionofcovid-19classifiers","venue":null,"work_id":"5cb1eaaf-83aa-49cd-9e59-1a5036aae312","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.794022Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:b44cc3ce3b45774cdce56b840d84730cf184daa92d52b2b9c7f316eed38b3d49","observation_id":"e45d6fc2-6a46-468b-9442-2b2277fc1f19","resolution":{"observed_at":"2026-08-11T21:53:46.265353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.253452Z","title":"Optimising chest x-rays for image analysis by identi- fying and removing confounding factors","venue":null,"work_id":"235f241c-9a94-4ce5-8f26-6c0bff5d1b93","year":2022},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.796082Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:e6e3f193cc2ccbba65c4b31a3b6540d638e0106528506c32d46352da22151df0","observation_id":"7a8d1793-71cb-4235-8e68-af1bb3962112","resolution":{"observed_at":"2026-08-11T21:53:46.256611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.244124Z","title":"Shortcut learning in medical image segmentation","venue":null,"work_id":"997ba242-165d-4f9a-8ead-4c442f4c7307","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.798329Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:8328349a1450bddd222227d7a4912796c29267ba3826bc1d6909f40fc8822942","observation_id":"c2050af6-735b-4b2a-8c99-149540fb7594","resolution":{"observed_at":"2026-08-11T21:53:46.247203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.236061Z","title":"Source matters: Source dataset impact on model robustness in medical imaging","venue":null,"work_id":"b410ce07-df79-41ee-9e6b-a6519f3419a8","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.801253Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:ed28ed4ad41bb6e56be23a039d4e04bedbf3f4bd2c478e60226334a133493c4d","observation_id":"8c42f6d2-fb20-46d6-9fa8-324de4c7d689","resolution":{"observed_at":"2026-08-11T21:53:46.238888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.229198Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"ace659cc-5243-4de6-96bb-4654587ea4d0","year":2009},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.803095Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:9500d46e3828d1e8e282b473af98d79def557167333317a8f2f09a7d2fc4c0d4","observation_id":"01f15ae3-95cd-4be8-ad76-07bbf6d50303","resolution":{"observed_at":"2026-08-11T21:53:46.231859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.220438Z","title":"Radimagenet: an open radiologic deep learning research dataset for effective trans- fer learning","venue":null,"work_id":"28cced32-b3d4-4288-9037-d171e93f76e1","year":2022},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.805563Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:f7f5b66c9c7db6048457d3c7345f43a7cfe8bf8bed1065f860b98e118d4f4b0e","observation_id":"097b6b2f-6191-430d-84a8-7ac9a51755b5","resolution":{"observed_at":"2026-08-11T21:53:46.223990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.212640Z","title":null,"venue":null,"work_id":"887366f0-5bf4-4952-b242-678580272142","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.807801Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:7c457635ffdaf165e9ff747635e83770cd360a1e85b47441d45b430100646510","observation_id":"8877b258-6ff0-4599-a633-07a1d05c0dca","resolution":{"observed_at":"2026-08-11T21:53:46.215078Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.205172Z","title":"Transparent medical image ai via an image–text foundation model grounded in medical literature","venue":null,"work_id":"a370bf22-747e-4c23-a238-96b705dccbe9","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.811261Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:8bb81e55014e7053acb70ced045f672fcc16e7a432f58136ae6f58836f25f5b9","observation_id":"2614784f-d1a2-4e95-8f15-3b529f71ed5f","resolution":{"observed_at":"2026-08-11T21:53:46.208087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.195088Z","title":"Concept bottleneck models","venue":null,"work_id":"2c64a16b-bd90-469d-b881-bf704a74abb3","year":2020},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.814040Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:81ddc3826846535ad6896d0665a60ca75cee5cce7df109c959a9c99a0a2ac275","observation_id":"c7383ecc-9224-4943-bc04-60a2cb23d94c","resolution":{"observed_at":"2026-08-11T21:53:46.198209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.185527Z","title":"Padchest: A large chest x-ray image dataset with multi-label annotated reports","venue":null,"work_id":"af624b39-3e0f-45f9-87ab-84e6b983a974","year":2020},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.817163Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:15bb11119e82da21389d58495e6954531004af5d74965c0d816bbc33edc54be0","observation_id":"60df08c8-f055-4d62-a978-6d29258f7e2a","resolution":{"observed_at":"2026-08-11T21:53:46.188299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.178251Z","title":"Chexpert: A large chest radiograph dataset with uncertainty labels and ex- pert comparison","venue":null,"work_id":"f03a7f02-f0c6-478c-95cc-4b6566aad2a9","year":2019},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.819789Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:30d3c8ee3391ed2f23034910e0cbdc7473e48e3c2b8b222f612b69a5be7ebac8","observation_id":"d8bc09a8-51bc-4e98-8f74-9ff8cf2f6fcb","resolution":{"observed_at":"2026-08-11T21:53:46.181013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.170710Z","title":"Chestx-ray8: Hospital-scale chest x-ray database and bench- marks on weakly-supervised classification and localization of common thorax dis- eases","venue":null,"work_id":"3a0ac8e8-4878-4c85-8f3d-13c5b9a00410","year":2017},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.822265Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:3b990faf3472bcbcbc3f7925a65100170b095002a32d97fbced37e7efe858ec3","observation_id":"88e801ca-9347-4dfa-8d57-8c406cb1a057","resolution":{"observed_at":"2026-08-11T21:53:46.173449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.163514Z","title":"Chexmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images","venue":null,"work_id":"fedf8b65-c2b6-41c8-9875-d582ab962746","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.824771Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:fe57b958a693717a8c45bfb83f9fb8179535f690251741ccced6622889b38436","observation_id":"fbe80a51-2ffd-46d6-9198-cba313ad42cf","resolution":{"observed_at":"2026-08-11T21:53:46.166515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.155003Z","title":"Reverse classi- fication accuracy: predicting segmentation performance in the absence of ground truth","venue":null,"work_id":"fd5afc32-5fef-4c49-a694-3203502ecbc5","year":2017},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.827229Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:40f2887308c2be0fd7b9bd813bfd64af93ae9cf891c7871318ea150f62a5d087","observation_id":"afae7da9-f4e8-4156-bf41-bbf7c7da1821","resolution":{"observed_at":"2026-08-11T21:53:46.157870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.146209Z","title":"Cháks.u: A glaucoma specific fundus image database.Scientific data, 10(1):70, 2023","venue":null,"work_id":"61194a29-1bc3-44e8-b9e5-ee6b4272b00b","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.829991Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:b679d9883290747c00dc028be8f87ff845fa28ba7b14a234f7003c958265b5d8","observation_id":"35dcfd1b-4c49-4cbe-9de6-33c3d8ede818","resolution":{"observed_at":"2026-08-11T21:53:46.149333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.137616Z","title":"Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation","venue":null,"work_id":"f7c14913-02b2-4f8d-9d56-cbc6bd3510be","year":2004},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.832236Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:ee440c95cdbde7700a4c742c2b0ab5f5428b533e4a298eaa0a2097cec4f1473d","observation_id":"4aa559c8-7390-44d1-b2a8-3af4c998260d","resolution":{"observed_at":"2026-08-11T21:53:46.140879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:45.835029Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.835029Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:8c9a0665bcf500e60642f298d9953ec3514ac115d60aedb7f7ea91151e9b478a","observation_id":"0e74a7ce-9d2f-46de-adde-72f66636229b","resolution":{"observed_at":"2026-08-11T21:53:45.835029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2501.10727","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:45.974091Z","title":"In the picture: Medical imaging datasets, artifacts, and their living review.arXiv preprint arXiv:2501.10727, 2025","venue":null,"work_id":"69717d2b-da5d-44ff-9d90-09b51fed4631","year":2025},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.837588Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:9cdf9531a28a8f909e9b440d205d1f4dd40feaaa1c0577e3e2939c265b23575d","observation_id":"c984d449-b128-491b-9568-7a92661e55e1","resolution":{"observed_at":"2026-08-11T21:53:45.978163Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:45.840310Z","title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.840310Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:57f0bbe2557931020a904d94aeea13ec622fc34e71829c8120865b212abb1eef","observation_id":"dc9e8708-1b8b-4cff-b902-f7345c8f079f","resolution":{"observed_at":"2026-08-11T21:53:45.840310Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.120382Z","title":"Fast implementation of delong’s algorithm for comparing the areas under correlated receiver operating characteristic curves.IEEE Signal Processing Letters, 21(11):1389–1393, 2014","venue":null,"work_id":"48c6b913-7ee9-41e0-9729-3d88f5d2be99","year":2014},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.843511Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:6915b0f30ef306c288d7f9b03a9c62d53be0d67edd7c4de4d3c3d47e039a3c6a","observation_id":"b35321b0-55a4-4973-bed5-eff2d206db8d","resolution":{"observed_at":"2026-08-11T21:53:46.124337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.112152Z","title":"Classification of copd with multiple in- stance learning","venue":null,"work_id":"5e03b419-82ba-4b21-8802-8bf1bac39895","year":2014},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.846251Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:db548a4b91c60aa89408a31ff2f743489a4561e9c6aabfa9b16e6c4324f71ce4","observation_id":"85370209-1007-48d9-a11a-988f3656dd34","resolution":{"observed_at":"2026-08-11T21:53:46.114823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.104612Z","title":"A new method using deep learning to predict the response to cardiac resyn- chronization therapy","venue":null,"work_id":"d52c9fcd-2b79-44db-abdc-e3232b76beff","year":2025},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.848879Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:acffb9a9cda8fe505ada8f206223fc55d4a92faaaad1e2a1e9d4617dd0456231","observation_id":"182ea064-74d1-4154-8b61-9ac6f476dd90","resolution":{"observed_at":"2026-08-11T21:53:46.107531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:45.851617Z","title":"Visualizing data using t-sne.Jour- nal of machine learning research, 9(11), 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.851617Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:44181160129faf07dac7a315a9c27e49eaf5be33ebfadec2b38e5e4f3904654d","observation_id":"dac4bb9c-657b-4cbf-ab32-6f74c787aedf","resolution":{"observed_at":"2026-08-11T21:53:45.851617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.092201Z","title":"A unified approach to interpreting model pre- dictions","venue":null,"work_id":"3861b941-922e-494b-bc43-1490f8a23ada","year":2017},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.854409Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:3e76d891312cff942e2870d8b66f01ab7b094ec839bf12bff0415950ee746977","observation_id":"5aa98d03-85ff-4b24-aa46-c96ac712a35f","resolution":{"observed_at":"2026-08-11T21:53:46.094930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.084407Z","title":"Navigating the maze of explainable ai: A systematic approach to evaluating methods and metrics","venue":null,"work_id":"ec315283-1d73-4bae-a573-28fedf77557a","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.858832Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:dd178c1b259914ecf9bc61aa5e00bea3708f9b5b8944f423482c14e9ee880bad","observation_id":"e9e78d42-64e2-4bf5-902b-91fd17656d5b","resolution":{"observed_at":"2026-08-11T21:53:46.087578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.076357Z","title":"Impossibility theorems for feature attribution.Proceedings of the National Academy of Sciences, 121(2):e2304406120, 2024","venue":null,"work_id":"18317d84-6566-4fd7-a3e4-d6c3a19be75e","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.862332Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:8616ff516aeaeb3473a823d08326e66e2267891c26c823635669571bd6600ef8","observation_id":"4d4e511d-70e3-42dd-9586-fe87447a015e","resolution":{"observed_at":"2026-08-11T21:53:46.079330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:45.865829Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.865829Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:91bc1643cff8c59c9eb603b7cd9cda8bf258dece785bb3547cdf608318c5ce55","observation_id":"f7df0a0e-547d-4a8b-92f9-3e0a8b9c2c11","resolution":{"observed_at":"2026-08-11T21:53:45.865829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.063758Z","title":"Automatic detection of glaucoma via fundus imaging and artificial intelligence: A review.Survey of ophthalmology, 68(1):17–41, 2023","venue":null,"work_id":"3b2ac8f7-3002-4bdf-b8f8-0aa473e0e550","year":2023},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.868391Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:ab27198a730ae893204580ca1662c9146b1f72b18c376841a07d3b8422e3b66a","observation_id":"bf1f39a6-f3cd-4d07-913b-e13c7be16b31","resolution":{"observed_at":"2026-08-11T21:53:46.066849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.055926Z","title":"Optic disc diameter influences the ability to detect glaucomatous disc damage.Acta ophthalmologica, 71(1):122–129, 1993","venue":null,"work_id":"35a175e8-b967-4530-a004-4f79a78a5402","year":1993},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.870853Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:56b9729ec37e6c5ec4b95a670bb77071abf60a93b10e7d23ace36ae0b0014054","observation_id":"9c433e25-b497-4c2e-97a0-5a8e3446f50f","resolution":{"observed_at":"2026-08-11T21:53:46.058867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.049693Z","title":"Optic disc size, an important consideration in the glaucoma evaluation","venue":null,"work_id":"fa5fc143-aaa7-430d-af01-e5b44b56658f","year":1999},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.874009Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:d40f02e55eb7d7f5f032bf22c6c5a5a022cd89948125de67f699233ce1b1964e","observation_id":"ab3d3cb3-1b5c-460f-b422-bfb4c9572ace","resolution":{"observed_at":"2026-08-11T21:53:46.052005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.042689Z","title":"Model-based cleaning of the quilt-1m pathology dataset for text-conditional image synthesis","venue":null,"work_id":"0a30bec5-8223-4fa1-a930-8c974034fc7d","year":null},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.875862Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:e40b0e930da778abda95a5ee09199b953e9d7ef97d00fec2eb6350714dbb5dd2","observation_id":"505e9d2a-0ef3-4021-a17e-7a0eb41a30ba","resolution":{"observed_at":"2026-08-11T21:53:46.045493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.035036Z","title":"Investigating the quality of dermamnist and fitzpatrick17k dermatological image datasets.Scientific Data, 12(1):196, 2025","venue":null,"work_id":"9ea6779c-7349-497f-8769-42d38b607b70","year":2025},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.877887Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:2627ca87921cf11e38964dcf7b19440b7fe234ade74f9a9713ad9c61534f487b","observation_id":"d7e8ab45-8cbb-48c9-a462-52e157e1fe82","resolution":{"observed_at":"2026-08-11T21:53:46.038026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.03782","last_updated":"2024-11-06T09:18:05Z","snapshot_observed_at":"2026-08-12T22:06:37.955435Z","submitted_at":"2024-11-06T09:18:05Z","title":"Navigating the landscape of multimodal AI in medicine: a scoping review on technical challenges and clinical applications","version":1},"cited_work":{"arxiv_id":"2411.03782","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.03782","snapshot_observed_at":"2026-08-11T21:53:45.908527Z","title":"Navigating the landscape of multimodal AI in medicine: a scoping review on technical challenges and clinical applications","venue":"cs.AI","work_id":"1d42d8d0-1c85-4078-9076-a0b9cd7bed59","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.879624Z"},"links":{"cited_paper":"/paper/2411.03782","citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:d3b639a0fb601b533fde7d9de807615a35b57279658510b8ad03f87f19545147","observation_id":"f85c0307-7ee6-4a30-9f31-c3f950e649cc","resolution":{"observed_at":"2026-08-11T21:53:45.914827Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.027196Z","title":"The risk of shortcut- ting in deep learning algorithms for medical imaging research.Scientific Reports, 14(1):29224, 2024","venue":null,"work_id":"e098a477-1198-4069-937d-332bef795563","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.881707Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:d375ecf377ffa469db62930153ef523999283f6a83a3949e398ed5b90b8c00eb","observation_id":"d71fd064-d754-46f2-84b4-9410dd8d0cdd","resolution":{"observed_at":"2026-08-11T21:53:46.030487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.018885Z","title":"Are vision transformers robust to spurious correlations? International Journal of Computer Vision, 132(3):689–709, 2024","venue":null,"work_id":"f8df1573-92a0-4ba4-9eee-ef5c2c1de8ba","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.883661Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:88dc79ae77dabe36cc993762944e4ea579e083ef47bbec1aaa29d7ee70c0387f","observation_id":"12183bb8-2bbe-4103-8555-edbe2025b17e","resolution":{"observed_at":"2026-08-11T21:53:46.022060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T21:53:46.009960Z","title":"Metrics reloaded: recommendations for image analysis validation","venue":null,"work_id":"521abe47-c156-4fb5-b6fa-f1aeb96745b4","year":2024},"citing_paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T21:53:45.886010Z"},"links":{"citing_paper":"/paper/2412.04030"},"observation_digest":"sha256:01a79e35fb278af4143fd25a09016292872e2eb2fa9d24fc93c5dd9ff4e9df62","observation_id":"6b7ffe8d-1536-4f4f-ad28-b574dd890f3e","resolution":{"observed_at":"2026-08-11T21:53:46.013119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.04030","last_updated":"2025-05-22T09:31:56Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T21:40:49.428229Z","submitted_at":"2024-12-05T10:06:58Z","title":"Mask of truth: model sensitivity to unexpected regions of medical images"},"reference_resolution":{"displayed":66,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":2,"verified_fuzzy":54},"total_outbound_references":66},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2412.04030."}