{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4WXYLLYIOO566CUA56F75K6RO2","short_pith_number":"pith:4WXYLLYI","schema_version":"1.0","canonical_sha256":"e5af85af0873bbef0a80ef8bfeabd176a1fc565c34563f25ffa485247a2513a6","source":{"kind":"arxiv","id":"1901.10277","version":3},"attestation_state":"computed","paper":{"title":"High-Quality Self-Supervised Deep Image Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jaakko Lehtinen, Samuli Laine, Tero Karras, Timo Aila","submitted_at":"2019-01-29T13:37:16Z","abstract_excerpt":"We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images. The training does not need access to clean reference images, or explicit pairs of corrupted images, and can thus be applied in situations where such data is unacceptably expensive or impossible to acquire. We build on a recent technique that removes the need for reference data by employing networks with a \"blind spot\" in the receptive field, and significantly improve two key aspects: image quality and training efficiency. Our result quality is on par with state-of-t"},"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":"1901.10277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-29T13:37:16Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"81c3075f78e63c193f88e69267584d98725f694c04f84d46d4a251587b3faa8c","abstract_canon_sha256":"3cce34b9d50ccade5267c1e9c60b9d137603c599e9381688c23498860ad10f3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:02.546829Z","signature_b64":"SchXHQNsUqf1DOtkyaJyRcMn9wTmjgssAkqjgEPygDX9cv4HSTp7lSICbSAdb/2yjqMzODb3ny1oe8ihDAUxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5af85af0873bbef0a80ef8bfeabd176a1fc565c34563f25ffa485247a2513a6","last_reissued_at":"2026-07-05T00:15:02.546395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:02.546395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Quality Self-Supervised Deep Image Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jaakko Lehtinen, Samuli Laine, Tero Karras, Timo Aila","submitted_at":"2019-01-29T13:37:16Z","abstract_excerpt":"We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images. The training does not need access to clean reference images, or explicit pairs of corrupted images, and can thus be applied in situations where such data is unacceptably expensive or impossible to acquire. We build on a recent technique that removes the need for reference data by employing networks with a \"blind spot\" in the receptive field, and significantly improve two key aspects: image quality and training efficiency. Our result quality is on par with state-of-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10277","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/1901.10277/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":"1901.10277","created_at":"2026-07-05T00:15:02.546456+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10277v3","created_at":"2026-07-05T00:15:02.546456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10277","created_at":"2026-07-05T00:15:02.546456+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WXYLLYIOO56","created_at":"2026-07-05T00:15:02.546456+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WXYLLYIOO566CUA","created_at":"2026-07-05T00:15:02.546456+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WXYLLYI","created_at":"2026-07-05T00:15:02.546456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11109","citing_title":"Deploying Self-Supervised Learning for Real Seismic Data Denoising","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2","json":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2.json","graph_json":"https://pith.science/api/pith-number/4WXYLLYIOO566CUA56F75K6RO2/graph.json","events_json":"https://pith.science/api/pith-number/4WXYLLYIOO566CUA56F75K6RO2/events.json","paper":"https://pith.science/paper/4WXYLLYI"},"agent_actions":{"view_html":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2","download_json":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2.json","view_paper":"https://pith.science/paper/4WXYLLYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10277&json=true","fetch_graph":"https://pith.science/api/pith-number/4WXYLLYIOO566CUA56F75K6RO2/graph.json","fetch_events":"https://pith.science/api/pith-number/4WXYLLYIOO566CUA56F75K6RO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2/action/storage_attestation","attest_author":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2/action/author_attestation","sign_citation":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2/action/citation_signature","submit_replication":"https://pith.science/pith/4WXYLLYIOO566CUA56F75K6RO2/action/replication_record"}},"created_at":"2026-07-05T00:15:02.546456+00:00","updated_at":"2026-07-05T00:15:02.546456+00:00"}