{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XSN5JRPLWVV43H6KRWPDL5V2PD","short_pith_number":"pith:XSN5JRPL","schema_version":"1.0","canonical_sha256":"bc9bd4c5ebb56bcd9fca8d9e35f6ba78dd67946df2b483fe9f8694113ff0b4ce","source":{"kind":"arxiv","id":"2607.23347","version":1},"attestation_state":"computed","paper":{"title":"Trainable Nonexpansive Denoisers for Contractive Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Aditya Banerjee, Arghya Sinha, Kunal N. Chaudhury, Trishit Mukherjee","submitted_at":"2026-07-25T19:54:42Z","abstract_excerpt":"Trainable denoisers with Lipschitz control have become central to convergent image reconstruction. However, training neural networks that simultaneously offer strong denoising performance and global Lipschitz guarantees is challenging. Existing approaches enforce Lipschitz control only empirically, providing no guarantees beyond the training data. In this work, we show that by exploiting the action of permutations on the image lattice, we can constrain a neural architecture that is globally nonexpansive (Lipschitz bound $\\leqslant 1$). We integrate the proposed denoiser with forward imaging op"},"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":"2607.23347","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-07-25T19:54:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"982ae318b6cba228da7e4c5c278e4031df77a6eda34b014e44d3d538a4cab268","abstract_canon_sha256":"aeadbe514d0f91fcb2a2f7e7f5ff1da035c661830721a2dcbcf7448b5a645834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:48.670250Z","signature_b64":"KeZPl9U6ZmJF0UTlSM7a4u+UBCuAh/HfN7zoUYAaWnPxbWvX70+T9+ECP9EmQzdG72HJnLWJbQnvCO68QDoDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc9bd4c5ebb56bcd9fca8d9e35f6ba78dd67946df2b483fe9f8694113ff0b4ce","last_reissued_at":"2026-07-28T01:22:48.669466Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:48.669466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trainable Nonexpansive Denoisers for Contractive Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Aditya Banerjee, Arghya Sinha, Kunal N. Chaudhury, Trishit Mukherjee","submitted_at":"2026-07-25T19:54:42Z","abstract_excerpt":"Trainable denoisers with Lipschitz control have become central to convergent image reconstruction. However, training neural networks that simultaneously offer strong denoising performance and global Lipschitz guarantees is challenging. Existing approaches enforce Lipschitz control only empirically, providing no guarantees beyond the training data. In this work, we show that by exploiting the action of permutations on the image lattice, we can constrain a neural architecture that is globally nonexpansive (Lipschitz bound $\\leqslant 1$). We integrate the proposed denoiser with forward imaging op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23347","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/2607.23347/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":"2607.23347","created_at":"2026-07-28T01:22:48.669873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23347v1","created_at":"2026-07-28T01:22:48.669873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23347","created_at":"2026-07-28T01:22:48.669873+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSN5JRPLWVV4","created_at":"2026-07-28T01:22:48.669873+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSN5JRPLWVV43H6K","created_at":"2026-07-28T01:22:48.669873+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSN5JRPL","created_at":"2026-07-28T01:22:48.669873+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/XSN5JRPLWVV43H6KRWPDL5V2PD","json":"https://pith.science/pith/XSN5JRPLWVV43H6KRWPDL5V2PD.json","graph_json":"https://pith.science/api/pith-number/XSN5JRPLWVV43H6KRWPDL5V2PD/graph.json","events_json":"https://pith.science/api/pith-number/XSN5JRPLWVV43H6KRWPDL5V2PD/events.json","paper":"https://pith.science/paper/XSN5JRPL"},"agent_actions":{"view_html":"https://pith.science/pith/XSN5JRPLWVV43H6KRWPDL5V2PD","download_json":"https://pith.science/pith/XSN5JRPLWVV43H6KRWPDL5V2PD.json","view_paper":"https://pith.science/paper/XSN5JRPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23347&json=true","fetch_graph":"https://pith.science/api/pith-number/XSN5JRPLWVV43H6KRWPDL5V2PD/graph.json","fetch_events":"https://pith.science/api/pith-number/XSN5JRPLWVV43H6KRWPDL5V2PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSN5JRPLWVV43H6KRWPDL5V2PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSN5JRPLWVV43H6KRWPDL5V2PD/action/storage_attestation","attest_author":"https://pith.science/pith/XSN5JRPLWVV43H6KRWPDL5V2PD/action/author_attestation","sign_citation":"https://pith.science/pith/XSN5JRPLWVV43H6KRWPDL5V2PD/action/citation_signature","submit_replication":"https://pith.science/pith/XSN5JRPLWVV43H6KRWPDL5V2PD/action/replication_record"}},"created_at":"2026-07-28T01:22:48.669873+00:00","updated_at":"2026-07-28T01:22:48.669873+00:00"}