{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4DMDPREH67Y7LYVR62IJPKJ6DL","short_pith_number":"pith:4DMDPREH","schema_version":"1.0","canonical_sha256":"e0d837c487f7f1f5e2b1f69097a93e1ad3b39d4fe2bb7f7d1583f47d258bba12","source":{"kind":"arxiv","id":"2006.02379","version":4},"attestation_state":"computed","paper":{"title":"The Neural Tangent Link Between CNN Denoisers and Non-Local Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","eess.SP"],"primary_cat":"cs.CV","authors_text":"Juli\\'an Tachella, Junqi Tang, Mike Davies","submitted_at":"2020-06-03T16:50:54Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are now a well-established tool for solving computational imaging problems. Modern CNN-based algorithms obtain state-of-the-art performance in diverse image restoration problems. Furthermore, it has been recently shown that, despite being highly overparameterized, networks trained with a single corrupted image can still perform as well as fully trained networks. We introduce a formal link between such networks through their neural tangent kernel (NTK), and well-known non-local filtering techniques, such as non-local means or BM3D. The filtering function ass"},"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":"2006.02379","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-03T16:50:54Z","cross_cats_sorted":["eess.IV","eess.SP"],"title_canon_sha256":"067e2e95b0615f316ddb1b05139930d01a7908de4a54eeb91a66c1e0ef2df744","abstract_canon_sha256":"77b450d49352639c4a522e8183948e88b23d1029e0aeb823701d93a57e472ad0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:56.852467Z","signature_b64":"xI6D2DcTbThdRHYOiKpW+7kkTIZ31FsD9dFcxITD1bfprXjLxPLeBgpJxBmoDL6W93B8ssH9sV12XNwQYXuuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0d837c487f7f1f5e2b1f69097a93e1ad3b39d4fe2bb7f7d1583f47d258bba12","last_reissued_at":"2026-07-05T09:22:56.852109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:56.852109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Neural Tangent Link Between CNN Denoisers and Non-Local Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","eess.SP"],"primary_cat":"cs.CV","authors_text":"Juli\\'an Tachella, Junqi Tang, Mike Davies","submitted_at":"2020-06-03T16:50:54Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are now a well-established tool for solving computational imaging problems. Modern CNN-based algorithms obtain state-of-the-art performance in diverse image restoration problems. Furthermore, it has been recently shown that, despite being highly overparameterized, networks trained with a single corrupted image can still perform as well as fully trained networks. We introduce a formal link between such networks through their neural tangent kernel (NTK), and well-known non-local filtering techniques, such as non-local means or BM3D. The filtering function ass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02379","kind":"arxiv","version":4},"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/2006.02379/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":"2006.02379","created_at":"2026-07-05T09:22:56.852170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.02379v4","created_at":"2026-07-05T09:22:56.852170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02379","created_at":"2026-07-05T09:22:56.852170+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DMDPREH67Y7","created_at":"2026-07-05T09:22:56.852170+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DMDPREH67Y7LYVR","created_at":"2026-07-05T09:22:56.852170+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DMDPREH","created_at":"2026-07-05T09:22:56.852170+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/4DMDPREH67Y7LYVR62IJPKJ6DL","json":"https://pith.science/pith/4DMDPREH67Y7LYVR62IJPKJ6DL.json","graph_json":"https://pith.science/api/pith-number/4DMDPREH67Y7LYVR62IJPKJ6DL/graph.json","events_json":"https://pith.science/api/pith-number/4DMDPREH67Y7LYVR62IJPKJ6DL/events.json","paper":"https://pith.science/paper/4DMDPREH"},"agent_actions":{"view_html":"https://pith.science/pith/4DMDPREH67Y7LYVR62IJPKJ6DL","download_json":"https://pith.science/pith/4DMDPREH67Y7LYVR62IJPKJ6DL.json","view_paper":"https://pith.science/paper/4DMDPREH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.02379&json=true","fetch_graph":"https://pith.science/api/pith-number/4DMDPREH67Y7LYVR62IJPKJ6DL/graph.json","fetch_events":"https://pith.science/api/pith-number/4DMDPREH67Y7LYVR62IJPKJ6DL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DMDPREH67Y7LYVR62IJPKJ6DL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DMDPREH67Y7LYVR62IJPKJ6DL/action/storage_attestation","attest_author":"https://pith.science/pith/4DMDPREH67Y7LYVR62IJPKJ6DL/action/author_attestation","sign_citation":"https://pith.science/pith/4DMDPREH67Y7LYVR62IJPKJ6DL/action/citation_signature","submit_replication":"https://pith.science/pith/4DMDPREH67Y7LYVR62IJPKJ6DL/action/replication_record"}},"created_at":"2026-07-05T09:22:56.852170+00:00","updated_at":"2026-07-05T09:22:56.852170+00:00"}