{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UPMGE2EKGPEMFX5ALR3YT6W3EI","short_pith_number":"pith:UPMGE2EK","schema_version":"1.0","canonical_sha256":"a3d862688a33c8c2dfa05c7789fadb222ba0e9d9baa37f5cf3dcc2199ac012d5","source":{"kind":"arxiv","id":"2403.15132","version":1},"attestation_state":"computed","paper":{"title":"Transfer CLIP for Generalizable Image Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Dong Liang, Jun Cheng, Shan Tan","submitted_at":"2024-03-22T11:33:04Z","abstract_excerpt":"Image denoising is a fundamental task in computer vision. While prevailing deep learning-based supervised and self-supervised methods have excelled in eliminating in-distribution noise, their susceptibility to out-of-distribution (OOD) noise remains a significant challenge. The recent emergence of contrastive language-image pre-training (CLIP) model has showcased exceptional capabilities in open-world image recognition and segmentation. Yet, the potential for leveraging CLIP to enhance the robustness of low-level tasks remains largely unexplored. This paper uncovers that certain dense features"},"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":"2403.15132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T11:33:04Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"b46556f74dcc4e20a0531cb6627588cfb06efea1ecb7565ab6eab11ce343d104","abstract_canon_sha256":"5fb9ad574645f1986811fc4950d4843dfffc3d34b321b3457decd937c4c6e07c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:30.794889Z","signature_b64":"wXhfXZJ/RjXzu7b6S5W3ommzs0llNYpFcd3F2C21HjQDgW9rbgJgHB2CTFyPqmYBpORRpSJnu1srfyfVh5CsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3d862688a33c8c2dfa05c7789fadb222ba0e9d9baa37f5cf3dcc2199ac012d5","last_reissued_at":"2026-07-05T07:59:30.794327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:30.794327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transfer CLIP for Generalizable Image Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Dong Liang, Jun Cheng, Shan Tan","submitted_at":"2024-03-22T11:33:04Z","abstract_excerpt":"Image denoising is a fundamental task in computer vision. While prevailing deep learning-based supervised and self-supervised methods have excelled in eliminating in-distribution noise, their susceptibility to out-of-distribution (OOD) noise remains a significant challenge. The recent emergence of contrastive language-image pre-training (CLIP) model has showcased exceptional capabilities in open-world image recognition and segmentation. Yet, the potential for leveraging CLIP to enhance the robustness of low-level tasks remains largely unexplored. This paper uncovers that certain dense features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15132","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/2403.15132/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":"2403.15132","created_at":"2026-07-05T07:59:30.794392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15132v1","created_at":"2026-07-05T07:59:30.794392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15132","created_at":"2026-07-05T07:59:30.794392+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPMGE2EKGPEM","created_at":"2026-07-05T07:59:30.794392+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPMGE2EKGPEMFX5A","created_at":"2026-07-05T07:59:30.794392+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPMGE2EK","created_at":"2026-07-05T07:59:30.794392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02967","citing_title":"Towards Robust Image Denoising with Scale Equivariance","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI","json":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI.json","graph_json":"https://pith.science/api/pith-number/UPMGE2EKGPEMFX5ALR3YT6W3EI/graph.json","events_json":"https://pith.science/api/pith-number/UPMGE2EKGPEMFX5ALR3YT6W3EI/events.json","paper":"https://pith.science/paper/UPMGE2EK"},"agent_actions":{"view_html":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI","download_json":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI.json","view_paper":"https://pith.science/paper/UPMGE2EK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15132&json=true","fetch_graph":"https://pith.science/api/pith-number/UPMGE2EKGPEMFX5ALR3YT6W3EI/graph.json","fetch_events":"https://pith.science/api/pith-number/UPMGE2EKGPEMFX5ALR3YT6W3EI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI/action/storage_attestation","attest_author":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI/action/author_attestation","sign_citation":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI/action/citation_signature","submit_replication":"https://pith.science/pith/UPMGE2EKGPEMFX5ALR3YT6W3EI/action/replication_record"}},"created_at":"2026-07-05T07:59:30.794392+00:00","updated_at":"2026-07-05T07:59:30.794392+00:00"}