{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CIFRHGIR4FSYVSLMBR7EGKAIGS","short_pith_number":"pith:CIFRHGIR","schema_version":"1.0","canonical_sha256":"120b139911e1658ac96c0c7e4328083481958d044ffc476cca921df0cb3bce1a","source":{"kind":"arxiv","id":"1902.05300","version":1},"attestation_state":"computed","paper":{"title":"On instabilities of deep learning in image reconstruction - Does AI come at a cost?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anders C. Hansen, Ben Adcock, Clarice Poon, Francesco Renna, Vegard Antun","submitted_at":"2019-02-14T11:14:58Z","abstract_excerpt":"Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper we demonstrate a crucial phenomenon: deep learning typically yields unstablemethods for image reconstruction. The instabilities usually occur in several forms: (1) tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction, (2) a small structural change, for example a tumour, may not be captured in the reconstructed image and (3) (a coun"},"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":"1902.05300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-14T11:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"1218159e41e3cb4caf3865ad69e3ba15d11ce4485100abf4ea73bd8f367cc7ce","abstract_canon_sha256":"591857ad3459ee760c0256512a0f2b02d88204e86ef49485239260c8fb12f565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:00.912077Z","signature_b64":"NoBEHvhDS3cfXgjxAgZWav8cPbmz69AfMnA6Q6xcd+nmKmN2Km+L4t31hxQYGnlcDpHsA1I4E/xVhkz4bMhtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"120b139911e1658ac96c0c7e4328083481958d044ffc476cca921df0cb3bce1a","last_reissued_at":"2026-07-05T01:02:00.911635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:00.911635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On instabilities of deep learning in image reconstruction - Does AI come at a cost?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anders C. Hansen, Ben Adcock, Clarice Poon, Francesco Renna, Vegard Antun","submitted_at":"2019-02-14T11:14:58Z","abstract_excerpt":"Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper we demonstrate a crucial phenomenon: deep learning typically yields unstablemethods for image reconstruction. The instabilities usually occur in several forms: (1) tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction, (2) a small structural change, for example a tumour, may not be captured in the reconstructed image and (3) (a coun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05300","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/1902.05300/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":"1902.05300","created_at":"2026-07-05T01:02:00.911692+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.05300v1","created_at":"2026-07-05T01:02:00.911692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05300","created_at":"2026-07-05T01:02:00.911692+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIFRHGIR4FSY","created_at":"2026-07-05T01:02:00.911692+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIFRHGIR4FSYVSLM","created_at":"2026-07-05T01:02:00.911692+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIFRHGIR","created_at":"2026-07-05T01:02:00.911692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.06792","citing_title":"Data Consistent Artifact Reduction for Limited Angle Tomography with Deep Learning Prior","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS","json":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS.json","graph_json":"https://pith.science/api/pith-number/CIFRHGIR4FSYVSLMBR7EGKAIGS/graph.json","events_json":"https://pith.science/api/pith-number/CIFRHGIR4FSYVSLMBR7EGKAIGS/events.json","paper":"https://pith.science/paper/CIFRHGIR"},"agent_actions":{"view_html":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS","download_json":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS.json","view_paper":"https://pith.science/paper/CIFRHGIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.05300&json=true","fetch_graph":"https://pith.science/api/pith-number/CIFRHGIR4FSYVSLMBR7EGKAIGS/graph.json","fetch_events":"https://pith.science/api/pith-number/CIFRHGIR4FSYVSLMBR7EGKAIGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS/action/storage_attestation","attest_author":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS/action/author_attestation","sign_citation":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS/action/citation_signature","submit_replication":"https://pith.science/pith/CIFRHGIR4FSYVSLMBR7EGKAIGS/action/replication_record"}},"created_at":"2026-07-05T01:02:00.911692+00:00","updated_at":"2026-07-05T01:02:00.911692+00:00"}