{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PPCSYRKJZ5MIO5WC7TEPNHVJ3N","short_pith_number":"pith:PPCSYRKJ","schema_version":"1.0","canonical_sha256":"7bc52c4549cf588776c2fcc8f69ea9db76302178531ab932255304233848fcf5","source":{"kind":"arxiv","id":"2011.04268","version":1},"attestation_state":"computed","paper":{"title":"Solving Inverse Problems With Deep Neural Networks -- Robustness Included?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Jan Macdonald, Martin Genzel, Maximilian M\\\"arz","submitted_at":"2020-11-09T09:33:07Z","abstract_excerpt":"In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems. Before such approaches can find application in safety-critical fields, a verification of their reliability appears mandatory. Recent works have pointed out instabilities of deep neural networks for several image reconstruction tasks. In analogy to adversarial attacks in classification, it was shown that slight distortions in the input domain may cause severe artifacts. The present article sheds new light on this concern, by conducting an extensive study of the robustness of deep-lear"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2011.04268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-09T09:33:07Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"38e71e135e2f845a1dd5539c2cb62acf7f8d0c12be0cb7b80d4a7371825bea68","abstract_canon_sha256":"05beaf0096bfd76a36f3f4a1c5fa0ba7e346f94e468b9301d51836e79184fa60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:04.183370Z","signature_b64":"8Z8BM3CPmjxpkAgRt/P5NMIthCrso1Qoj5zE2y6A2YdaS64UvA7Yzcvbpf0GS51y1bnaSNPZo2VdFCdREUfICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bc52c4549cf588776c2fcc8f69ea9db76302178531ab932255304233848fcf5","last_reissued_at":"2026-07-05T05:33:04.182872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:04.182872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Inverse Problems With Deep Neural Networks -- Robustness Included?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Jan Macdonald, Martin Genzel, Maximilian M\\\"arz","submitted_at":"2020-11-09T09:33:07Z","abstract_excerpt":"In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems. Before such approaches can find application in safety-critical fields, a verification of their reliability appears mandatory. Recent works have pointed out instabilities of deep neural networks for several image reconstruction tasks. In analogy to adversarial attacks in classification, it was shown that slight distortions in the input domain may cause severe artifacts. The present article sheds new light on this concern, by conducting an extensive study of the robustness of deep-lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04268","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.04268/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.04268","created_at":"2026-07-05T05:33:04.182937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.04268v1","created_at":"2026-07-05T05:33:04.182937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04268","created_at":"2026-07-05T05:33:04.182937+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPCSYRKJZ5MI","created_at":"2026-07-05T05:33:04.182937+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPCSYRKJZ5MIO5WC","created_at":"2026-07-05T05:33:04.182937+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPCSYRKJ","created_at":"2026-07-05T05:33:04.182937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16573","citing_title":"Optimization Landscapes Learned: Proxy Networks Boost Convergence in Physics-based Inverse Problems","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N","json":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N.json","graph_json":"https://pith.science/api/pith-number/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/graph.json","events_json":"https://pith.science/api/pith-number/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/events.json","paper":"https://pith.science/paper/PPCSYRKJ"},"agent_actions":{"view_html":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N","download_json":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N.json","view_paper":"https://pith.science/paper/PPCSYRKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.04268&json=true","fetch_graph":"https://pith.science/api/pith-number/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/graph.json","fetch_events":"https://pith.science/api/pith-number/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/action/storage_attestation","attest_author":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/action/author_attestation","sign_citation":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/action/citation_signature","submit_replication":"https://pith.science/pith/PPCSYRKJZ5MIO5WC7TEPNHVJ3N/action/replication_record"}},"created_at":"2026-07-05T05:33:04.182937+00:00","updated_at":"2026-07-05T05:33:04.182937+00:00"}