{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4CUOMHW7E6IWPBKAGZHBBPXQEP","short_pith_number":"pith:4CUOMHW7","schema_version":"1.0","canonical_sha256":"e0a8e61edf2791678540364e10bef023e25a8f16d02e55b00f73b6c09e04bfff","source":{"kind":"arxiv","id":"1903.06920","version":1},"attestation_state":"computed","paper":{"title":"Robust Super-Resolution GAN, with Manifold-based and Perception Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Suyash P. Awate, Uddeshya Upadhyay","submitted_at":"2019-03-16T13:45:09Z","abstract_excerpt":"Super-resolution using deep neural networks typically relies on highly curated training sets that are often unavailable in clinical deployment scenarios. Using loss functions that assume Gaussian-distributed residuals makes the learning sensitive to corruptions in clinical training sets. We propose novel loss functions that are robust to corruptions in training sets by modeling heavy-tailed non-Gaussian distributions on the residuals. We propose a loss based on an autoencoder-based manifold-distance between the super-resolved and high-resolution images, to reproduce realistic textural content "},"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":"1903.06920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-16T13:45:09Z","cross_cats_sorted":[],"title_canon_sha256":"a2cf1def820dfb1830f56281e74796729d1893e92b8c2f8dfbb2307c7e5800e8","abstract_canon_sha256":"6cd1d97a4633ba038bd647f4469c4db422805731f373387fd2e2d19b3ebf546e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:08.607400Z","signature_b64":"CVFbP+lNuvqMoId6A51pBbm22Yk9g7EoBf7nPoznl+yl0UrHQhnGobXnOd18TI7iTMbdkhRVjJ14Eoaf8jC3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0a8e61edf2791678540364e10bef023e25a8f16d02e55b00f73b6c09e04bfff","last_reissued_at":"2026-05-17T23:51:08.606834Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:08.606834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Super-Resolution GAN, with Manifold-based and Perception Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Suyash P. Awate, Uddeshya Upadhyay","submitted_at":"2019-03-16T13:45:09Z","abstract_excerpt":"Super-resolution using deep neural networks typically relies on highly curated training sets that are often unavailable in clinical deployment scenarios. Using loss functions that assume Gaussian-distributed residuals makes the learning sensitive to corruptions in clinical training sets. We propose novel loss functions that are robust to corruptions in training sets by modeling heavy-tailed non-Gaussian distributions on the residuals. We propose a loss based on an autoencoder-based manifold-distance between the super-resolved and high-resolution images, to reproduce realistic textural content "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06920","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":""},"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":"1903.06920","created_at":"2026-05-17T23:51:08.606928+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.06920v1","created_at":"2026-05-17T23:51:08.606928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06920","created_at":"2026-05-17T23:51:08.606928+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CUOMHW7E6IW","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CUOMHW7E6IWPBKA","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CUOMHW7","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP","json":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP.json","graph_json":"https://pith.science/api/pith-number/4CUOMHW7E6IWPBKAGZHBBPXQEP/graph.json","events_json":"https://pith.science/api/pith-number/4CUOMHW7E6IWPBKAGZHBBPXQEP/events.json","paper":"https://pith.science/paper/4CUOMHW7"},"agent_actions":{"view_html":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP","download_json":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP.json","view_paper":"https://pith.science/paper/4CUOMHW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.06920&json=true","fetch_graph":"https://pith.science/api/pith-number/4CUOMHW7E6IWPBKAGZHBBPXQEP/graph.json","fetch_events":"https://pith.science/api/pith-number/4CUOMHW7E6IWPBKAGZHBBPXQEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP/action/storage_attestation","attest_author":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP/action/author_attestation","sign_citation":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP/action/citation_signature","submit_replication":"https://pith.science/pith/4CUOMHW7E6IWPBKAGZHBBPXQEP/action/replication_record"}},"created_at":"2026-05-17T23:51:08.606928+00:00","updated_at":"2026-05-17T23:51:08.606928+00:00"}