{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BOU76QRH3IH5EWOZHDK64XWWQV","short_pith_number":"pith:BOU76QRH","schema_version":"1.0","canonical_sha256":"0ba9ff4227da0fd259d938d5ee5ed68543baddb539546c8966aedd09171753dd","source":{"kind":"arxiv","id":"1805.10531","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Learning with Stein's Unbiased Risk Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ali Mousavi, Christopher A. Metzler, Reinhard Heckel, Richard G. Baraniuk","submitted_at":"2018-05-26T20:01:15Z","abstract_excerpt":"Learning from unlabeled and noisy data is one of the grand challenges of machine learning. As such, it has seen a flurry of research with new ideas proposed continuously. In this work, we revisit a classical idea: Stein's Unbiased Risk Estimator (SURE). We show that, in the context of image recovery, SURE and its generalizations can be used to train convolutional neural networks (CNNs) for a range of image denoising and recovery problems without any ground truth data.\n  Specifically, our goal is to reconstruct an image $x$ from a noisy linear transformation (measurement) of the image. We consi"},"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":"1805.10531","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-26T20:01:15Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"2e256f1c4053ab070542e1034d0a60429695bac91904ea23237198a67b8d9574","abstract_canon_sha256":"97d632127678023074aac609819070a3e913ca010b19efbae933b441e5bd8553"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:33.215796Z","signature_b64":"ynsYupRYXWvhYjiXbLMUP1WmzI6gsudr9+mGHfDTntece3P1AiCOthy7NXnijam2nLCrf84rmsHFgs1tZFQUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ba9ff4227da0fd259d938d5ee5ed68543baddb539546c8966aedd09171753dd","last_reissued_at":"2026-07-05T01:21:33.215302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:33.215302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Learning with Stein's Unbiased Risk Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ali Mousavi, Christopher A. Metzler, Reinhard Heckel, Richard G. Baraniuk","submitted_at":"2018-05-26T20:01:15Z","abstract_excerpt":"Learning from unlabeled and noisy data is one of the grand challenges of machine learning. As such, it has seen a flurry of research with new ideas proposed continuously. In this work, we revisit a classical idea: Stein's Unbiased Risk Estimator (SURE). We show that, in the context of image recovery, SURE and its generalizations can be used to train convolutional neural networks (CNNs) for a range of image denoising and recovery problems without any ground truth data.\n  Specifically, our goal is to reconstruct an image $x$ from a noisy linear transformation (measurement) of the image. We consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10531","kind":"arxiv","version":3},"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/1805.10531/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":"1805.10531","created_at":"2026-07-05T01:21:33.215369+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10531v3","created_at":"2026-07-05T01:21:33.215369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10531","created_at":"2026-07-05T01:21:33.215369+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOU76QRH3IH5","created_at":"2026-07-05T01:21:33.215369+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOU76QRH3IH5EWOZ","created_at":"2026-07-05T01:21:33.215369+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOU76QRH","created_at":"2026-07-05T01:21:33.215369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04332","citing_title":"Learning-based Statistical Refinement for Denoising","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08272","citing_title":"Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV","json":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV.json","graph_json":"https://pith.science/api/pith-number/BOU76QRH3IH5EWOZHDK64XWWQV/graph.json","events_json":"https://pith.science/api/pith-number/BOU76QRH3IH5EWOZHDK64XWWQV/events.json","paper":"https://pith.science/paper/BOU76QRH"},"agent_actions":{"view_html":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV","download_json":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV.json","view_paper":"https://pith.science/paper/BOU76QRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10531&json=true","fetch_graph":"https://pith.science/api/pith-number/BOU76QRH3IH5EWOZHDK64XWWQV/graph.json","fetch_events":"https://pith.science/api/pith-number/BOU76QRH3IH5EWOZHDK64XWWQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV/action/storage_attestation","attest_author":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV/action/author_attestation","sign_citation":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV/action/citation_signature","submit_replication":"https://pith.science/pith/BOU76QRH3IH5EWOZHDK64XWWQV/action/replication_record"}},"created_at":"2026-07-05T01:21:33.215369+00:00","updated_at":"2026-07-05T01:21:33.215369+00:00"}