{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UH7MFSB5H6UKSZSQ66OQXZZ3KO","short_pith_number":"pith:UH7MFSB5","schema_version":"1.0","canonical_sha256":"a1fec2c83d3fa8a96650f79d0be73b538589454bbf96c9e1aac7499b41ac43fb","source":{"kind":"arxiv","id":"2602.11553","version":2},"attestation_state":"computed","paper":{"title":"Perception-based Image Denoising via Generative Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bella Bose, Nam Nguyen, Thinh Nguyen","submitted_at":"2026-02-12T04:21:26Z","abstract_excerpt":"Image denoising aims to remove noise while preserving structural details and perceptual realism, yet distortion-driven methods often produce over-smoothed reconstructions, especially under strong noise and distribution shift. This paper proposes a generative compression framework for perception-based denoising, where restoration is achieved by reconstructing from entropy-coded latent representations that enforce low-complexity structure, while generative decoders recover realistic textures via perceptual measures such as learned perceptual image patch similarity (LPIPS) loss and Wasserstein di"},"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":"2602.11553","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-12T04:21:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aec339686d193d2d0e6f6e586a8667c289fe8e66803a95cb870890598af05fb8","abstract_canon_sha256":"a439cdb92110c2f56fb6f35d7bf98136170c7810ce2cc6bb655c375fff7e2b5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:09.641654Z","signature_b64":"DPNU55oRc4bZHYVJZ/SKyvXpkTO+ML/KX3skrTLpWZesJQEfVwcv7rue35Jbi+lWN5//nXduZ6rKzr9MHtdIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1fec2c83d3fa8a96650f79d0be73b538589454bbf96c9e1aac7499b41ac43fb","last_reissued_at":"2026-05-20T00:02:09.640792Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:09.640792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perception-based Image Denoising via Generative Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bella Bose, Nam Nguyen, Thinh Nguyen","submitted_at":"2026-02-12T04:21:26Z","abstract_excerpt":"Image denoising aims to remove noise while preserving structural details and perceptual realism, yet distortion-driven methods often produce over-smoothed reconstructions, especially under strong noise and distribution shift. This paper proposes a generative compression framework for perception-based denoising, where restoration is achieved by reconstructing from entropy-coded latent representations that enforce low-complexity structure, while generative decoders recover realistic textures via perceptual measures such as learned perceptual image patch similarity (LPIPS) loss and Wasserstein di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11553","kind":"arxiv","version":2},"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/2602.11553/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":"2602.11553","created_at":"2026-05-20T00:02:09.640941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11553v2","created_at":"2026-05-20T00:02:09.640941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11553","created_at":"2026-05-20T00:02:09.640941+00:00"},{"alias_kind":"pith_short_12","alias_value":"UH7MFSB5H6UK","created_at":"2026-05-20T00:02:09.640941+00:00"},{"alias_kind":"pith_short_16","alias_value":"UH7MFSB5H6UKSZSQ","created_at":"2026-05-20T00:02:09.640941+00:00"},{"alias_kind":"pith_short_8","alias_value":"UH7MFSB5","created_at":"2026-05-20T00:02:09.640941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.11553","citing_title":"Perception-based Image Denoising via Generative Compression","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO","json":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO.json","graph_json":"https://pith.science/api/pith-number/UH7MFSB5H6UKSZSQ66OQXZZ3KO/graph.json","events_json":"https://pith.science/api/pith-number/UH7MFSB5H6UKSZSQ66OQXZZ3KO/events.json","paper":"https://pith.science/paper/UH7MFSB5"},"agent_actions":{"view_html":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO","download_json":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO.json","view_paper":"https://pith.science/paper/UH7MFSB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11553&json=true","fetch_graph":"https://pith.science/api/pith-number/UH7MFSB5H6UKSZSQ66OQXZZ3KO/graph.json","fetch_events":"https://pith.science/api/pith-number/UH7MFSB5H6UKSZSQ66OQXZZ3KO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO/action/storage_attestation","attest_author":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO/action/author_attestation","sign_citation":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO/action/citation_signature","submit_replication":"https://pith.science/pith/UH7MFSB5H6UKSZSQ66OQXZZ3KO/action/replication_record"}},"created_at":"2026-05-20T00:02:09.640941+00:00","updated_at":"2026-05-20T00:02:09.640941+00:00"}