{"as_of":"2026-08-19T07:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3c469e6d50e5f83048a34f739355dd1e2264e0d576947e2bf9b8c4dbc3ce45b5","coverage":[{"denominator":145,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T10:56:19.080121Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2608.02238/citation-record","integrity":"/paper/2608.02238/integrity","json":"/paper/2608.02238/citation-record.json","paper":"/paper/2608.02238"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:06.853672Z","title":"[Accessed July 2025]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:06.853672Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:1b3b3050550c8c05cbd881b9ffe430a77f4c432915e1e2fd9ba724a03a543a62","observation_id":"e0f43930-6db5-48f0-90be-13b507e56f1a","resolution":{"observed_at":"2026-08-04T10:56:06.853672Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:06.955821Z","title":"https://digital-strategy.ec.europa.eu/en/library/ ethics-guidelines-trustworthy-ai","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:06.955821Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:947bfbd0385daee2d542080890958ee37149224ee8b33c0b44a76678832c7c9a","observation_id":"c61cd9b3-a855-4044-bd3b-28285867b452","resolution":{"observed_at":"2026-08-04T10:56:06.955821Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:07.062321Z","title":"https://scikit-learn.org/stable/modules/ generated/sklearn.datasets.load_breast_cancer.html","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:07.062321Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:02114c1eb9c91fa0f9a6f330aa45d41dcecba7108416f6aadefd16d579c2efc8","observation_id":"9c4f7c8a-7231-46e4-a141-dec3c4d2d777","resolution":{"observed_at":"2026-08-04T10:56:07.062321Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:07.217158Z","title":"https://www.nist.gov/ trustworthy-and-responsible-ai","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:07.217158Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:39d5b08cdef7ce47638ee4b92ad049d9c6724388020ad5ee4f12ad06a100c85e","observation_id":"1d683cf4-c6ad-4d35-8356-21f52afa5870","resolution":{"observed_at":"2026-08-04T10:56:07.217158Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:07.372655Z","title":"From attribution maps to human-understandable explanations through concept relevance propagation.Nature Machine Intelligence, 5(9):1006– 1019, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:07.372655Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:c1146b1018c0a2c2f4b215e3e5d09491d929f20f67669b94df7a0e9fb77b7f9b","observation_id":"fac15744-411b-4238-b59b-2bcf06831a13","resolution":{"observed_at":"2026-08-04T10:56:07.372655Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:07.536381Z","title":"A systematic review of trustworthy and explainable artificial intelligence in healthcare: Assessment of quality, bias risk, and data fusion.Information Fusion, 96:156–191, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:07.536381Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:0fba399708dae8c33fae6af75663ab3fb47558d41a4e25dffb668f6f78d19483","observation_id":"412234e9-b78d-4c12-b528-0589c7c57a01","resolution":{"observed_at":"2026-08-04T10:56:07.536381Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.07415","last_updated":"2020-03-16T19:19:08Z","snapshot_observed_at":"2026-07-06T09:05:08.003418Z","submitted_at":"2020-03-16T19:19:08Z","title":"ActiLabel: A Combinatorial Transfer Learning Framework for Activity Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.07415","snapshot_observed_at":"2026-08-04T10:56:07.661354Z","title":"Actilabel: A combinatorial transfer learning framework for activity recognition.arXiv preprint arXiv:2003.07415, 2020","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:07.661354Z"},"links":{"cited_paper":"/paper/2003.07415","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:ed78b26a5e64c49a2f114f246b623adbb2d445fdae7e0cbac4862d5e3a8dd197","observation_id":"3e3e7509-9a5c-422c-a6b1-32bf6201d180","resolution":{"observed_at":"2026-08-04T10:56:07.661354Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:07.814624Z","title":"Evaluating the faithfulness of saliency maps in explaining deep learning models using realistic perturbations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:07.814624Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:2508b948c12cbf70963e9e3c58360b6883a75c49a8032b7ed030123686732340","observation_id":"5aaca59c-fdbf-4dd5-b58a-49f611e7fd82","resolution":{"observed_at":"2026-08-04T10:56:07.814624Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:07.877834Z","title":"Deep learning for ecg arrhythmia detection and classification: an overview of progress for period 2017–2023","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:07.877834Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:033d0071cdf147a1f782e6688bcb371a181e81c63d1f83bb59cba1000796173d","observation_id":"39fa9f40-4ceb-45cf-9405-9c5ff2cda4f4","resolution":{"observed_at":"2026-08-04T10:56:07.877834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01684","last_updated":"2024-11-01T15:46:35Z","snapshot_observed_at":"2026-08-16T14:55:40.218862Z","submitted_at":"2023-10-02T22:42:52Z","title":"Designing User-Centric Behavioral Interventions to Prevent Dysglycemia with Novel Counterfactual Explanations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01684","snapshot_observed_at":"2026-08-04T10:56:07.955384Z","title":"Designing user-centric behavioral interventions to prevent dysglycemia with novel counterfactual explanations.arXiv preprint arXiv:2310.01684, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:07.955384Z"},"links":{"cited_paper":"/paper/2310.01684","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:5ee7e9d6373d34635db4bafa0d1c0202b4ab15659fe8dae5d6e595a893ad689b","observation_id":"f6e238dc-d566-4bd6-9863-5692b7ccad3d","resolution":{"observed_at":"2026-08-04T10:56:07.955384Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:08.093982Z","title":"Glyman: Glycemic management using patient-centric counterfactuals","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:08.093982Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:96e88ed2742eb18ec9cad7ac48c9774aef7983c8af01cb3615c092f3bb2b29e2","observation_id":"869d9ca7-5ea9-4b0a-ba67-fe65844cbed4","resolution":{"observed_at":"2026-08-04T10:56:08.093982Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09846","last_updated":"2026-05-21T19:12:04Z","snapshot_observed_at":"2026-08-19T03:55:34.559372Z","submitted_at":"2025-04-14T03:32:39Z","title":"GlyTwin: Digital Twin for Glucose Control in Type 1 Diabetes Through Optimal Behavioral Modifications Using Patient-Centric Counterfactuals","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09846","snapshot_observed_at":"2026-08-04T10:56:08.247774Z","title":"Glytwin: Digital twin for glucose control in type 1 diabetes through optimal be- havioral modifications using patient-centric counterfactuals.arXiv preprint arXiv:2504.09846, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:08.247774Z"},"links":{"cited_paper":"/paper/2504.09846","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:863566927d2ce65e36880487e237f7a098cfccffe888580a2d729f40c49fab2a","observation_id":"991e5114-9bf2-4726-a383-4000f97deddd","resolution":{"observed_at":"2026-08-04T10:56:08.247774Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:08.359295Z","title":"Semi-factual explanations in ai","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:08.359295Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:a7f6d654f3afd0b59b7eb71b1cc9d934722b4d0f8d4af346fe652d0968fda746","observation_id":"b01284f0-fb0a-49a3-9a67-8cfed9a9a9a6","resolution":{"observed_at":"2026-08-04T10:56:08.359295Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:08.475016Z","title":"A hybrid method for imputation of missing values using optimized fuzzy c-means with support vector regression and a genetic algorithm","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:08.475016Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:d6898a2a7a920c1a1c0dbff723d82be1d3ddc0a2b0f182f36d451e233750a6ac","observation_id":"73ce5777-bb1a-4764-99b5-414f054e4955","resolution":{"observed_at":"2026-08-04T10:56:08.475016Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:08.617915Z","title":"Cudle: Learning under label scarcity to detect cannabis use in uncontrolled environments using wearables.IEEE Sensors Journal, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:08.617915Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:461eef3db46ade06d02bc65031bee2f5e392beddf587c8315bf49f0369de5584","observation_id":"13a43d61-3e42-48e4-81db-3a0560cc9445","resolution":{"observed_at":"2026-08-04T10:56:08.617915Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:08.730065Z","title":"Robust counterfactual explanations on graph neural networks.Advances in Neural Information Processing Systems, 34:5644–5655, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:08.730065Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:b0c47f2f37b1a38ddd1c0a862d8ce4b5f59a8900be48af676644d5909c506e8d","observation_id":"2af4206a-56ba-4391-a6a7-bf33948c242a","resolution":{"observed_at":"2026-08-04T10:56:08.730065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.01555","last_updated":"2023-12-04T00:54:04Z","snapshot_observed_at":"2026-08-16T14:38:01.659910Z","submitted_at":"2023-12-04T00:54:04Z","title":"Explainable AI is Responsible AI: How Explainability Creates Trustworthy and Socially Responsible Artificial Intelligence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.01555","snapshot_observed_at":"2026-08-04T10:56:08.882266Z","title":"Explainable ai is responsible ai: How explainability creates trustworthy and socially responsible artificial intelligence.arXiv preprint arXiv:2312.01555, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:08.882266Z"},"links":{"cited_paper":"/paper/2312.01555","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:907ebcec9f49f90721171fce9d6409695d45f7315021c3066a4f2108c26816fe","observation_id":"5bd2d025-f3ed-48e7-9821-280d4fc728ec","resolution":{"observed_at":"2026-08-04T10:56:08.882266Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:08.991132Z","title":"Application of explainable artificial intelligence in medical health: A systematic review of interpretability methods.Informatics in Medicine Unlocked, 40:101286, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:08.991132Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:aa713a4b60851c22c500233994ccf2c0f60483008484da2fbc3f1b309d25818b","observation_id":"b3805c61-0b40-4d7b-8468-2aab9d52af1f","resolution":{"observed_at":"2026-08-04T10:56:08.991132Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:09.095400Z","title":"Mhealth dataset.UCI machine learning repository, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:09.095400Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:818efc8e19063ed4b93473035e6adf1e20dda47317528a2dbc6305a3abac961d","observation_id":"04db2f51-04e3-4ea1-b4a7-18b67352ac41","resolution":{"observed_at":"2026-08-04T10:56:09.095400Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:09.203618Z","title":"Llama-nemotron: Efficient reasoning models.arXiv preprint arXiv:2505.00949, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:09.203618Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:e80a43268ec50f2da146aa7371ffeb6c9fb899ef3922ccc7bee81859510a38d9","observation_id":"60db2ee9-39c7-4b18-9a5a-d37f231b8729","resolution":{"observed_at":"2026-08-04T10:56:09.203618Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:09.348356Z","title":"Responsible development of clinical speech ai: Bridging the gap between clinical research and technology.NPJ Digital Medicine, 7(1):208, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:09.348356Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:429b9e0a661350a0a9f6a3014f412f80511f774ed4367afd5b5c77382c847370","observation_id":"94be71d4-5835-480f-ae17-0c119d154f6f","resolution":{"observed_at":"2026-08-04T10:56:09.348356Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:09.536018Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:09.536018Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:d9b5535f221d5a6c9699459eeb8d14a51c9c3994add5b00070e461686bd50d1b","observation_id":"5ffcff2b-677d-42dc-9e62-5a0cf7d63f99","resolution":{"observed_at":"2026-08-04T10:56:09.536018Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:09.685097Z","title":"Fine-tuning a llm using reinforcement learning from human feedback for a therapy chatbot application, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:09.685097Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:332393225ad6ef73a9381a05325e9b81fb47e564b918f59d5de7ec8fd351294e","observation_id":"b2262cb9-beaf-4b75-8979-5b87683fed19","resolution":{"observed_at":"2026-08-04T10:56:09.685097Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:09.802863Z","title":"Layer-wise relevance propagation for neural networks with local renor- malization layers","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:09.802863Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:bac78fc27c01dd95f18b56270ee91a1ae041d130c4a6f05e603ba48404230881","observation_id":"cd737b02-fd14-4719-abf3-4220f495fd28","resolution":{"observed_at":"2026-08-04T10:56:09.802863Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:09.984587Z","title":"Ethical issues in ai- enabled disease surveillance: perspectives from global health.Applied Sciences, 12(8):3890, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:09.984587Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:cc55de79eb264a311876a05b805cd2a502349203c783e82b732b75a9fbcde586","observation_id":"885c4d0a-5f9a-4931-8cf8-2b405f547318","resolution":{"observed_at":"2026-08-04T10:56:09.984587Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:10.108125Z","title":"Nice: an algorithm for nearest instance counterfactual explanations.Data mining and knowledge discovery, 38(5):2665–2703, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:10.108125Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:ccc44d5134c234553b4beaf724191c2276ada65248058e06fcec74c56a1d8c9b","observation_id":"2e6cbe35-7b87-4928-9494-1442a9258b51","resolution":{"observed_at":"2026-08-04T10:56:10.108125Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:10.231470Z","title":"Artificial intelligence revolution in turkish health consultancy: Development of llm-based virtual doctor assistants","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:10.231470Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:673d666cb5012b2432760bad2a75b2ae3aee34a51bcda953f66955638f1edee9","observation_id":"777fccc4-638b-4ee5-892c-4192abe17e91","resolution":{"observed_at":"2026-08-04T10:56:10.231470Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:10.346356Z","title":"e-snli: Nat- ural language inference with natural language explanations.Advances in Neural Information Processing Systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:10.346356Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:5eb2e8675eaefbe6d1c9d9c3990e88be296427995d6784db69f06a0b77492420","observation_id":"8ffc0d97-9bac-432f-889d-1ca1b0dec41e","resolution":{"observed_at":"2026-08-04T10:56:10.346356Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:10.500504Z","title":"Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:10.500504Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:60e5dfa33e03bf373d3898760fbb6ecd4142fb5c868927241c85b8438706514a","observation_id":"69de5e57-c084-47ca-b77c-181a065bfee4","resolution":{"observed_at":"2026-08-04T10:56:10.500504Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:10.618290Z","title":"Rlhf deciphered: A critical analysis of reinforcement learning from human feedback for llms.ACM Computing Surveys, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:10.618290Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:08592ffc95a4da96de7428a844a9bdb37690465ccffe291c4bedb2dc53353e75","observation_id":"f87548f1-a08d-4c5b-b62e-455f91dfce80","resolution":{"observed_at":"2026-08-04T10:56:10.618290Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:10.767591Z","title":"Smote: synthetic minority over-sampling technique.Journal of artificial intelligence research, 16:321– 357, 2002","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:10.767591Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:af97bba6f3edff5bae8cc0f9f5f22c07a293978070fb16e914d85afab11a0cd2","observation_id":"657e79ce-47e0-4cc5-adc7-40ced2a7706b","resolution":{"observed_at":"2026-08-04T10:56:10.767591Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:10.911326Z","title":"Diabetes: Non-invasive blood glucose monitoring using federated learning with biosensor signals.Biosensors, 15(4):255, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:10.911326Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:956a5deecb15da429365e42f0a6e784c86241cdd34d1021eecf84c7367c383e4","observation_id":"59aae1cf-3266-4fdc-89e5-91b161672633","resolution":{"observed_at":"2026-08-04T10:56:10.911326Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:11.116630Z","title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:11.116630Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:5ded10be2ffa1de658a018494da4616bb1769a2b32238bcfdf3c79a0d40f8d32","observation_id":"8d790a67-d7b8-4963-913e-43d7fc90a672","resolution":{"observed_at":"2026-08-04T10:56:11.116630Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:11.262949Z","title":"Do models explain themselves? counterfactual simulatability of natural language explanations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:11.262949Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:bfb48d5928878adaf7f1c428ce329e0b9f686913a7d8aa77eeefe416ccf42d4c","observation_id":"a0adc7a3-d401-478d-8edc-02c433e2fb24","resolution":{"observed_at":"2026-08-04T10:56:11.262949Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:11.362556Z","title":"How machine learning is used to study addiction in digital healthcare: A systematic review.International Journal of Information Management Data Insights, 3(2):100175, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:11.362556Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:a9ec2bc580376a6c240c10ef6f2af48604e3a6fc0e7e65b4503905142d5d0396","observation_id":"f9f222ea-15c8-4b24-b2e4-d25150f985d9","resolution":{"observed_at":"2026-08-04T10:56:11.362556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.10762","last_updated":"2020-09-22T18:46:05Z","snapshot_observed_at":"2026-08-03T04:53:20.545395Z","submitted_at":"2020-09-22T18:46:05Z","title":"Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.10762","snapshot_observed_at":"2026-08-04T10:56:11.478245Z","title":"Role of orthogonality constraints in improving properties of deep networks for image classification.arXiv preprint arXiv:2009.10762, 2020","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:11.478245Z"},"links":{"cited_paper":"/paper/2009.10762","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:adedf4ddfdd652dc97c86a2d45d907d2d871ac7545d158f66f08255b93ceb2e8","observation_id":"77bc3378-4aa0-4c5f-8761-e0310f6db8ba","resolution":{"observed_at":"2026-08-04T10:56:11.478245Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:11.614076Z","title":"Evaluating visual explanations of attention maps for transformer-based medical imaging","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:11.614076Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:f5d4a4211d8e069b6bf90145fe7e4827b10f655b5e19a76f8a980932e7a3458c","observation_id":"ce09eb24-04ef-4a01-9042-70d32fb51aac","resolution":{"observed_at":"2026-08-04T10:56:11.614076Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:11.802831Z","title":"The future landscape of large language models in medicine.Communications medicine, 3(1):141, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:11.802831Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:3651036df5fbe9beb71ce489977a5a0545c1f04f1e1cd4c6501df6e3538173a0","observation_id":"c2d935c0-02c3-49a1-8f27-00fa432c27ac","resolution":{"observed_at":"2026-08-04T10:56:11.802831Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:11.919136Z","title":"Evaluation of individual and ensemble probabilistic forecasts of covid-19 mortality in the united states.Proceedings of the National Academy of Sciences, 119(15):e2113561119, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:11.919136Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:65829df03936199976dd4cbcfa1f1e88af48455ec9de45e9c224b007e40559f6","observation_id":"dc1f8c17-f3e5-478f-b4a4-f0df2606a3f5","resolution":{"observed_at":"2026-08-04T10:56:11.919136Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:12.041287Z","title":"Bias in medical ai: Implications for clinical decision-making.PLOS Digital Health, 3(11):e0000651, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:12.041287Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:da5a09d2a8400ec535ace7c42484780a3a60d3ae16b2271bc33bcb2e08cb51ab","observation_id":"c5f7e5fa-34c6-40dc-bba2-4f0428f62a5f","resolution":{"observed_at":"2026-08-04T10:56:12.041287Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:12.144681Z","title":"Multi-objective coun- terfactual explanations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:12.144681Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:697e42fbfc928dd4fe8af87cb9ff9476517f658e7625036daebfa0e868aa393f","observation_id":"9c1deb1c-60b6-45e9-a817-d1f8f94e5ddd","resolution":{"observed_at":"2026-08-04T10:56:12.144681Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:12.236073Z","title":"A multitask learning approach to per- sonalized blood glucose prediction.IEEE Journal of Biomedical and Health Informatics, 26(1):436–445, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:12.236073Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:b91345a1b4a8dcc27b70ac8e0c0c1f9b21f415ca19c2b59eb49930af855b652e","observation_id":"fdab3e1a-99ff-4b23-a702-5cb698b350a6","resolution":{"observed_at":"2026-08-04T10:56:12.236073Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:12.354405Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:12.354405Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:1aadc30ef8cd936ebb77a174b1a38112d05d79bcb7a674c0471a7a950110259c","observation_id":"76053707-3e68-4d69-994d-2e7557f8131e","resolution":{"observed_at":"2026-08-04T10:56:12.354405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08608","last_updated":"2017-03-02T19:32:10Z","snapshot_observed_at":"2026-08-17T15:51:42.391912Z","submitted_at":"2017-02-28T02:19:20Z","title":"Towards A Rigorous Science of Interpretable Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.08608","snapshot_observed_at":"2026-08-04T10:56:12.525477Z","title":"Towards a rigorous science of interpretable machine learning.arXiv preprint arXiv:1702.08608, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:12.525477Z"},"links":{"cited_paper":"/paper/1702.08608","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:2956c02b0ae9be802f0bc6e8ec1b68378a6593c4720ce192dba3c729a92deded","observation_id":"d542d561-74c5-4ca8-9ceb-6c595c6d1622","resolution":{"observed_at":"2026-08-04T10:56:12.525477Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:12.668869Z","title":"Revealing hidden context bias in segmentation and object detection through concept-specific explanations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:12.668869Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:13756d5b5083dc5c9c23de179ee8f4926702ce4823609267449b2e5f7ba1f812","observation_id":"bed62e30-5647-49f0-b08f-a3b98cafc051","resolution":{"observed_at":"2026-08-04T10:56:12.668869Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:12.798515Z","title":"Haloscope: Harnessing unlabeled llm generations for hallucination detection.Advances in Neural Information Processing Systems, 37:102948– 102972, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:12.798515Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:882fd22c5efc10527991db925b44334f3e256c64f9f7658b5c399f23473b2eba","observation_id":"a0d54bbb-6ade-4dc1-a4df-1e9627c7c7e8","resolution":{"observed_at":"2026-08-04T10:56:12.798515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-04T10:56:12.922417Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:12.922417Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:1c21f010775aeedbc5918892c431f8ffd197b72cb8f426b34d6f509fa65db940","observation_id":"3a69a47f-4d92-4b35-9aad-573968628ea0","resolution":{"observed_at":"2026-08-04T10:56:12.922417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09919","last_updated":"2025-02-14T05:07:38Z","snapshot_observed_at":"2026-08-18T05:44:07.081257Z","submitted_at":"2025-02-14T05:07:38Z","title":"AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09919","snapshot_observed_at":"2026-08-04T10:56:13.091531Z","title":"Attengluco: Multimodal transformer-based blood glucose forecasting on ai-readi dataset","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:13.091531Z"},"links":{"cited_paper":"/paper/2502.09919","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:eb84d9cf598ea99f71fe46d7f289140ce2ca3d28963c2090825531af55dacaf4","observation_id":"a0917726-707a-41bf-8dc5-ff2a72a7b93f","resolution":{"observed_at":"2026-08-04T10:56:13.091531Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:13.225056Z","title":"A trustworthy ai reality-check: the lack of transparency of artificial intelligence products in healthcare.Frontiers in Digital Health, 6:1267290, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:13.225056Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:95ee4d0db3321b87ba6b61e093e684c5663ae44265adc4dc2d343768c9b7cbf2","observation_id":"bc3dab67-e0be-40ef-a62f-c864c1ff3496","resolution":{"observed_at":"2026-08-04T10:56:13.225056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18864","last_updated":"2025-02-26T06:17:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-26T06:17:13Z","title":"Towards an AI co-scientist","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18864","snapshot_observed_at":"2026-08-04T10:56:13.352133Z","title":"Towards an ai co-scientist.arXiv preprint arXiv:2502.18864, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:13.352133Z"},"links":{"cited_paper":"/paper/2502.18864","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:4b9dc69541193d15035af74023bd3c1929d1562d9f75022704a076201136a253","observation_id":"59c9c260-9113-4f79-a118-7cf2561c71c7","resolution":{"observed_at":"2026-08-04T10:56:13.352133Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:13.456637Z","title":"Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study.Critical Care, 28(1):349, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:13.456637Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:8a0746d0b8cab5b16b2833b0f87ab3879be26268ec94fba4f142ba6b21e81abe","observation_id":"6166d10a-66e3-410d-adf6-3ac1f450a40b","resolution":{"observed_at":"2026-08-04T10:56:13.456637Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:13.608104Z","title":"Domain adaptation for medical image analysis: a survey.IEEE Transactions on Biomedical Engineering, 69(3):1173–1185, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:13.608104Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:9e1fb596317c4fc308f021a1ce31f39194a5e792366d5af35715c4ab9bc8be47","observation_id":"d3949cbb-2552-4aec-b090-74bebd9a9633","resolution":{"observed_at":"2026-08-04T10:56:13.608104Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:13.754865Z","title":"Counterfactual explanations and how to find them: literature review and benchmarking.Data Mining and Knowledge Discovery, 38(5):2770–2824, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:13.754865Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:b736a020490d4b669883090ae065870df66b818494cd65258476966e02b3d76e","observation_id":"3e9accf3-a1e7-4ecd-ba16-1a75166c3ca9","resolution":{"observed_at":"2026-08-04T10:56:13.754865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-04T10:56:13.878365Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning.arXiv preprint arXiv:2501.12948, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:13.878365Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:80eb952ec825907ce35b4fb2efd592fa9bfe8e35eb16b3f531d17ae5cd322679","observation_id":"18dfdd1e-8a20-4673-98ee-a9d3b360afc6","resolution":{"observed_at":"2026-08-04T10:56:13.878365Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:14.048640Z","title":"Trustworthy artificial intelligence in medical imaging.PET clinics, 17(1):1, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:14.048640Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:816f681842dc5603f160c7bd6398bec751c296d7baf82da797f2fe966117ad1d","observation_id":"b7b8c192-d93d-464d-9833-8831ad8a3c61","resolution":{"observed_at":"2026-08-04T10:56:14.048640Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:14.158383Z","title":"Adasyn: Adaptive synthetic sampling approach for imbalanced learning","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:14.158383Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:c8f3ba5297a626aee2c344682724469dbc28c0a1ecf19fa09f14517453362de3","observation_id":"2135004d-29f8-44e2-a2cc-446c55b37241","resolution":{"observed_at":"2026-08-04T10:56:14.158383Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:14.307598Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:14.307598Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:ff7adc51e9c12f93e098a0800184eeab159f82b0ce66987b23ce84b09a800977","observation_id":"db38aa72-58ec-4a79-ac7e-1711fc754c4e","resolution":{"observed_at":"2026-08-04T10:56:14.307598Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:14.454689Z","title":"Exploring inherent sensor redundancy for automotive anomaly detection","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:14.454689Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:ec873c6cc1190437384035ca1be2d55e5e3d06d1274ba34b38d076052700c7c6","observation_id":"ac901a6b-a315-45d1-886b-353b7b15e35b","resolution":{"observed_at":"2026-08-04T10:56:14.454689Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:14.615415Z","title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.ACM Transactions on Information Systems, 43(2):1–55, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:14.615415Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:f89ae7d7d365eb353f915393a3a6158e0dcdca997ca78fe34d277cede5c632e0","observation_id":"93ff3b13-fb6f-4151-bba6-13f8221ff798","resolution":{"observed_at":"2026-08-04T10:56:14.615415Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:14.731803Z","title":"Self-supervised learning for medical image classification: a systematic review and implementation guidelines.NPJ Digital Medicine, 6(1):74, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:14.731803Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:a0262e79e5a44d8ba1ddbdbf91d601411538ff75eb5f6e535f4a0fb5c9fd516d","observation_id":"84f070b3-9ccc-454d-afe8-56f864599bba","resolution":{"observed_at":"2026-08-04T10:56:14.731803Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:14.905900Z","title":"Energy-efficient missing data recovery in wearable devices: A novel search-based approach","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:14.905900Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:7ff8e772d416792c51b102e72464d37306d24beead6a80246e7190f8a2b20797","observation_id":"23830338-8148-4b69-9545-afff25672411","resolution":{"observed_at":"2026-08-04T10:56:14.905900Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:15.042603Z","title":"Cim: A novel clustering-based energy-efficient data impu- tation method for human activity recognition.ACM Transactions on Embedded Computing Systems, 22(5s):1–26, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:15.042603Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:d2336ee384741dc665bf6fb2cd177a1dd25cdc4cf4b54c806803568438da982d","observation_id":"46993dee-5238-4f97-af14-7ba1d57bdedf","resolution":{"observed_at":"2026-08-04T10:56:15.042603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16720","last_updated":"2026-04-30T02:46:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-21T18:04:31Z","title":"OpenAI o1 System Card","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16720","snapshot_observed_at":"2026-08-04T10:56:15.192061Z","title":"Openai o1 system card","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:15.192061Z"},"links":{"cited_paper":"/paper/2412.16720","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:b834d074c3982368d09d41eed90e6bc86463fd555d2c7e9bd84acdc3bd234e12","observation_id":"8bcc7fbc-81dd-41d9-af23-0b380ece61d3","resolution":{"observed_at":"2026-08-04T10:56:15.192061Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:15.356539Z","title":"Requirements for trustworthy artificial intelligence–a review","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:15.356539Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:9ff9f8b2cfd19c3ad71109d8fe4e60753e8924ed3adb2ac52dd533cb1a1eeb44","observation_id":"3cd8e532-7f0f-49e6-8681-d9f6ff3d7d91","resolution":{"observed_at":"2026-08-04T10:56:15.356539Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:15.513749Z","title":"Trustworthy artificial intelligence: a review.ACM computing surveys (CSUR), 55(2):1–38, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:15.513749Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:f0235ad3a817283f589641a7661412cb6e09b9b4d5b2ff3d7e6e2f710c77739f","observation_id":"854219e8-04a4-478a-aa53-f7dd86692a88","resolution":{"observed_at":"2026-08-04T10:56:15.513749Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:15.630596Z","title":"Identifying medical diagnoses and treatable diseases by image-based deep learning.cell, 172(5):1122– 1131, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:15.630596Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:ee0d2336e94be48f446b15436de406580ca54b9c313ccd4247fb68ac9dfa521a","observation_id":"e3b63d89-ae8d-415f-8171-3c1fede91a2b","resolution":{"observed_at":"2026-08-04T10:56:15.630596Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:15.762119Z","title":"The promise and perils of artificial intelligence in advancing participatory science and health equity in public health.JMIR Public Health and Surveillance, 11(1):e65699, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:15.762119Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:8a00d8dabfbd67ad2c2cae34596a9788d4497c0b2988e9db99a84ede4b49e3a7","observation_id":"84724487-2fa8-4a31-9374-7c7932675b98","resolution":{"observed_at":"2026-08-04T10:56:15.762119Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:15.905220Z","title":"Large language models are zero-shot reasoners.Advances in neural information processing systems, 35:22199–22213, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:15.905220Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:4510401e7a33baddb49361e65de6ec13226c672ce4f2f533e2ff2acc72151069","observation_id":"7d3ee582-4ede-4866-ab67-a2880ced0eef","resolution":{"observed_at":"2026-08-04T10:56:15.905220Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:16.021378Z","title":"Establishing and evaluating trustworthy ai: overview and research challenges.Frontiers in Big Data, 7:1467222, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:16.021378Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:8b4cb309ee59ad53146c6160d3687f93017d655376f8dfcb8b5b5cad9c238e0f","observation_id":"c3aca629-9a17-4f56-bf3a-a99917cec774","resolution":{"observed_at":"2026-08-04T10:56:16.021378Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:16.164585Z","title":"Self-supervised learning in medicine and healthcare.Nature Biomedical Engineering, 6(12):1346–1352, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:16.164585Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:1934fd8122b9cb22e86637d8866087d6c682e1dd45eb02823f46f63bc5b16630","observation_id":"35929166-045a-46d5-a8ca-869b6b55daf7","resolution":{"observed_at":"2026-08-04T10:56:16.164585Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:16.284047Z","title":"Trustworthy ai in the age of pervasive computing and big data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:16.284047Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:61e57d8eb6cef1537fae964d7371adddc95b6cfbaf42ddf6dd005ddc9c89edc2","observation_id":"826c3506-eb07-4e22-92f3-b74efea871e0","resolution":{"observed_at":"2026-08-04T10:56:16.284047Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:16.436665Z","title":"dr llm, what do i have?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:16.436665Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:438e49d38c38902eabea5fc28d44aa1ca0fafa14b30f7cb8a85e2b4a9e394901","observation_id":"c63e989f-f6b0-44fc-ad84-9c84529550ba","resolution":{"observed_at":"2026-08-04T10:56:16.436665Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:16.575919Z","title":"Retrieval- augmented generation for knowledge-intensive nlp tasks.Advances in Neural Information Processing Systems, 33:9459–9474, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:16.575919Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:b1fbecc4d112d3d1aa55b8cd9573db961ae2991db7fd8542045ed84075f2ab46","observation_id":"ea2a4ba5-4bab-42c4-8790-0e81e857f365","resolution":{"observed_at":"2026-08-04T10:56:16.575919Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:16.753212Z","title":"Trustworthy ai: From principles to practices.ACM Computing Surveys, 55(9):1–46, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:16.753212Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:ff6f350650dcafc34ab88418a748026b2e38b3abb02d5c699e008bae2fc613ae","observation_id":"e01185c5-c9d1-4e4c-82e9-aedd5c7c09fd","resolution":{"observed_at":"2026-08-04T10:56:16.753212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.02976","last_updated":"2022-09-07T07:47:58Z","snapshot_observed_at":"2026-08-16T16:34:15.096349Z","submitted_at":"2022-09-07T07:47:58Z","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.02976","snapshot_observed_at":"2026-08-04T10:56:16.859067Z","title":"Yolov6: A single-stage object detection framework for industrial applications.arXiv preprint arXiv:2209.02976, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:16.859067Z"},"links":{"cited_paper":"/paper/2209.02976","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:915d737e707bdad1cca73529a0b1b03ab2953e587a41c78a5e91f696231131eb","observation_id":"ab3dca9a-2c7f-495a-bb53-87687251101b","resolution":{"observed_at":"2026-08-04T10:56:16.859067Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:16.973608Z","title":"Early prediction of alzheimer’s disease and related dementias using real-world electronic health records.Alzheimer’s & Dementia, 19(8):3506–3518, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:16.973608Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:eadcac9f9a22544fc105b12455a2c9c808aaf25bc14470359a19507eeae7cc65","observation_id":"be92703e-2677-4fef-9191-03d9eb973a63","resolution":{"observed_at":"2026-08-04T10:56:16.973608Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:17.051412Z","title":"Llms for relational reasoning: How far are we? InProceedings of the 1st International Workshop on Large Language Models for Code, pages 119–126, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.051412Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:f2ccf3291ba5af6a65f976ba64e90976b797985c0d27fbd8849651b09e141d71","observation_id":"696810ae-570e-42c5-9a46-45de81543bda","resolution":{"observed_at":"2026-08-04T10:56:17.051412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05318","last_updated":"2024-10-05T05:21:48Z","snapshot_observed_at":"2026-08-16T13:12:22.849830Z","submitted_at":"2024-10-05T05:21:48Z","title":"Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05318","snapshot_observed_at":"2026-08-04T10:56:17.135111Z","title":"Improving llm reasoning through scaling inference computation with collaborative verification","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.135111Z"},"links":{"cited_paper":"/paper/2410.05318","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:a5d6875c022665432b50057060f1d75b557a12771c337f905019184b14b7abf1","observation_id":"0d5ec4b6-e78b-420a-b80b-2d430e5ba00a","resolution":{"observed_at":"2026-08-04T10:56:17.135111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.05374","last_updated":"2024-03-21T00:21:14Z","snapshot_observed_at":"2026-08-02T17:09:20.540788Z","submitted_at":"2023-08-10T06:43:44Z","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.05374","snapshot_observed_at":"2026-08-04T10:56:17.217228Z","title":"Trustworthy llms: a survey and guideline for evaluating large language models’ alignment.arXiv preprint arXiv:2308.05374, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.217228Z"},"links":{"cited_paper":"/paper/2308.05374","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:2e5238eacadd58ab6a2e7166d4715428587d90ef889de52d53d54584997f6769","observation_id":"ab61dac6-8463-454b-80d2-2f3b800d43f0","resolution":{"observed_at":"2026-08-04T10:56:17.217228Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:17.291378Z","title":"Shap: A unified approach to interpreting model predictions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.291378Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:185b7aa3e7d1e9420da4deb236cf7c7bfe131c3c36e7185b4c1f5f13f909cfb3","observation_id":"4b586f01-dd7d-4a02-8334-6a1e02efe000","resolution":{"observed_at":"2026-08-04T10:56:17.291378Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:17.381020Z","title":"Clegg, Andrea Cavallaro, and Hamed Haddadi","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.381020Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:feb3e179d8ecc2ecbee83d4c7cbe70105cde7abb052eee779598c03a3982a1b9","observation_id":"6f785a3e-e15f-4708-9498-0a7ff8bf898e","resolution":{"observed_at":"2026-08-04T10:56:17.381020Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:17.453163Z","title":"Clegg, Andrea Cavallaro, and Hamed Haddadi","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.453163Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:6e297302b2ad890b3347b378bccf2f7c218fb4c8936e8783535594ed39a78dc7","observation_id":"9f11365f-45c8-419d-a565-d499a9ecb589","resolution":{"observed_at":"2026-08-04T10:56:17.453163Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:17.533968Z","title":"Racette, Dorothy D","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.533968Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:05bec97dbb1daf9edd2a2d7a8bb46deea2701126c2f615f7381db2e00718e2b6","observation_id":"6fcdc625-60de-4825-8adf-11c15c89a359","resolution":{"observed_at":"2026-08-04T10:56:17.533968Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.16091","last_updated":"2025-03-20T12:32:35Z","snapshot_observed_at":"2026-08-16T12:48:17.688025Z","submitted_at":"2025-03-20T12:32:35Z","title":"AIMI: Leveraging Future Knowledge and Personalization in Sparse Event Forecasting for Treatment Adherence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.16091","snapshot_observed_at":"2026-08-04T10:56:17.635979Z","title":"Aimi: Leveraging future knowl- edge and personalization in sparse event forecasting for treatment adherence.arXiv preprint arXiv:2503.16091, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.635979Z"},"links":{"cited_paper":"/paper/2503.16091","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:4f4f83ef4d9a9c3993571fbcd1b08cce49e8855ff57e573fee960636191980b4","observation_id":"e70aebf4-e5bc-4e08-9f89-bdb807aa9287","resolution":{"observed_at":"2026-08-04T10:56:17.635979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09635","last_updated":"2026-04-28T16:51:59Z","snapshot_observed_at":"2026-08-14T06:01:34.581978Z","submitted_at":"2024-10-12T20:21:00Z","title":"Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09635","snapshot_observed_at":"2026-08-04T10:56:17.696571Z","title":"Use of what-if scenarios to help explain artificial intelligence models for neonatal health.arXiv preprint arXiv:2410.09635, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.696571Z"},"links":{"cited_paper":"/paper/2410.09635","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:de4e36337eb5867e692578069178ab2131a15e8c0d40f85ff0a7855cff641115","observation_id":"32ba2cd5-094c-41da-9a27-b21dd8dabf08","resolution":{"observed_at":"2026-08-04T10:56:17.696571Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:17.781656Z","title":"Neonatal risk modeling and prediction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.781656Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:6c1e7ab509c05170d9532c56238fbe102b569257d83d496c919de76d3e9b8931","observation_id":"406ad538-c2b0-44ec-a803-bd9a0083883e","resolution":{"observed_at":"2026-08-04T10:56:17.781656Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:17.841706Z","title":"Mul- timodal time-series activity forecasting for adaptive lifestyle intervention design","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.841706Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:b10382eb7e0da03f1ea6293dc38a414e837c6a26625f442a20592b1d02d748cf","observation_id":"dabab563-ce6b-4828-9c93-2f4b7cfa4117","resolution":{"observed_at":"2026-08-04T10:56:17.841706Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09643","last_updated":"2024-10-12T20:44:00Z","snapshot_observed_at":"2026-08-17T10:50:36.454057Z","submitted_at":"2024-10-12T20:44:00Z","title":"Multimodal Physical Activity Forecasting in Free-Living Clinical Settings: Hunting Opportunities for Just-in-Time Interventions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09643","snapshot_observed_at":"2026-08-04T10:56:17.910558Z","title":"Multimodal physical activity forecasting in free-living clinical settings: Hunting opportunities for just-in-time interventions.arXiv preprint arXiv:2410.09643, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.910558Z"},"links":{"cited_paper":"/paper/2410.09643","citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:80d3ca0d2e70519b728e4cf79b078e9cb67e6355288c690ec79cf266e7bd3803","observation_id":"45a3da25-0d71-4ea0-b297-91f348ae35b3","resolution":{"observed_at":"2026-08-04T10:56:17.910558Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:17.968156Z","title":"Designing deep neural networks robust to sensor failure in mobile health environments","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:17.968156Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:654aeae3422e837bf60ca31eb03e4518c18a11d57eb2264dff9ef8fab30220bd","observation_id":"e9fd9537-60fc-43da-ac6e-a97fd92a8f10","resolution":{"observed_at":"2026-08-04T10:56:17.968156Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.045236Z","title":"Sensors and healthcare 5.0: transformative shift in virtual care through emerging digital health technologies","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.045236Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:1ec33c11462264480583b80352afe1b70583b0fe21e51fc8ec374fe9d3b4227f","observation_id":"11ff52d8-79f5-4259-a9d4-5d4167d1f5f7","resolution":{"observed_at":"2026-08-04T10:56:18.045236Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.105955Z","title":"A comprehensive study on fidelity metrics for xai.Information Processing & Management, 62(1):103900, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.105955Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:434e58c2cdb5a0ce2ba272e06a399f8a96ba883e14fca6721b086152b4df8542","observation_id":"59325db4-2738-40a4-bd32-22bb64ca5a84","resolution":{"observed_at":"2026-08-04T10:56:18.105955Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.161651Z","title":"Labelmerger: Learning activities in uncontrolled environments","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.161651Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:5688a6a731f1b6601033961c17ef90016801201e2245cb87a6513b989aa5122c","observation_id":"98f94498-b6a7-4a07-9d62-ba44feba887e","resolution":{"observed_at":"2026-08-04T10:56:18.161651Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.234613Z","title":"A multidisciplinary survey and framework for design and evaluation of explainable ai systems.ACM Transactions on Interactive Intelligent Systems (TiiS), 11(3-4):1–45, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.234613Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:301c51aea6b342f4c218d5911840c4d70be69d8d4bf643b92137b2f959e577ce","observation_id":"8740fce6-7de1-4f0a-8eb5-69771e4657d5","resolution":{"observed_at":"2026-08-04T10:56:18.234613Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.328688Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.328688Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:aec863071213ec10c9a409d96dc4a63064b781317e7112d0e4422c5ca6b0d8a3","observation_id":"f5db1d20-58af-4081-b806-e24e0f21ddad","resolution":{"observed_at":"2026-08-04T10:56:18.328688Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.446764Z","title":"Predicting sepsis using deep learning across international sites: a retrospective development and validation study.EClinicalMedicine, 62, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.446764Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:29c9f0fc76b4ddeb0b4539e9ae296ef4f47b4b0bf1d349c0756e29a5f7567883","observation_id":"d917fa6c-f623-4bd8-aa22-bce7b0eaa715","resolution":{"observed_at":"2026-08-04T10:56:18.446764Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.610984Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.610984Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:a39e8ec91a5c612b09d4eebcacbe801c97ee86317990e154930aee8dc8f33ddb","observation_id":"13ff2069-7a48-4448-b439-a10e819e815d","resolution":{"observed_at":"2026-08-04T10:56:18.610984Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.731200Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.731200Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:2761af5b5c6ce3df3b6dbf195c7b62098d461529d115ae20b8e908bc3b417576","observation_id":"de086e3a-bce5-4b28-a876-3bb378fbd9e6","resolution":{"observed_at":"2026-08-04T10:56:18.731200Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.815208Z","title":"Explaining machine learning classifiers through diverse counterfactual explanations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.815208Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:7951237f840be941510383d27972f8b006d60a2b1d6f35fcf20609ced3d362cc","observation_id":"63ec5e33-38ad-4112-8907-897b2b53c456","resolution":{"observed_at":"2026-08-04T10:56:18.815208Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:18.921457Z","title":"Rnas-cl: Robust neural architecture search by cross-layer knowledge distillation.International Journal of Computer Vision, 132(12):5698–5717, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:18.921457Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:7d06764ed434f40d0f9e8fc26cd3e4aa259abfe4ec68817dc768a9ef187550f8","observation_id":"c92fd196-8dca-4e57-a9aa-78e4c50e99f7","resolution":{"observed_at":"2026-08-04T10:56:18.921457Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:56:19.080121Z","title":"Multimodal deep learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-04T10:56:19.080121Z"},"links":{"citing_paper":"/paper/2608.02238"},"observation_digest":"sha256:5e73a7f306c5e2efc2f96969666d3ccbcfc6cc9c39c698385258df03eedf8b03","observation_id":"d6744630-e9a2-4b81-bbcb-00a3eeefdea7","resolution":{"observed_at":"2026-08-04T10:56:19.080121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.02238","last_updated":"2026-08-03T13:51:12Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-16T21:08:24.750102Z","submitted_at":"2026-08-03T13:51:12Z","title":"Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":100,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":145},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 100 of 145 outbound references and 0 inbound Pith citation observations for arXiv:2608.02238."}