{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PTPZAGBCUAC66PSC56IWZFO225","short_pith_number":"pith:PTPZAGBC","schema_version":"1.0","canonical_sha256":"7cdf901822a005ef3e42ef916c95dad75301faceb01701fe9fec074bb69ee2ba","source":{"kind":"arxiv","id":"2211.12461","version":3},"attestation_state":"computed","paper":{"title":"A Neural-Network-Based Convex Regularizer for Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Alexis Goujon, Michael Unser, Pakshal Bohra, Sebastian Neumayer, Stanislas Ducotterd","submitted_at":"2022-11-22T18:19:10Z","abstract_excerpt":"The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in reconstruction quality. Unfortunately, these new methods often lack reliability and explainability, and there is a growing interest to address these shortcomings while retaining the boost in performance. In this work, we tackle this issue by revisiting regularizers that are the sum of convex-ridge functions. The gradient of such regularizers is parameterized by a neural network that has a single hidden layer with increasing and learnable activation functions. This neural ne"},"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":"2211.12461","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2022-11-22T18:19:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f62c32ca41a1ea396830ba0f3686b1898073e0a2ddb74e360601091637ee767b","abstract_canon_sha256":"0898a92f665a14b028866632629ade718a48cb41c3ea23da348a6f18c75d7735"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:28.674460Z","signature_b64":"6VP/Sd300i/jOkINNFKBMJoakeO4dJfH2NUj0EB15lsQpVTkCYAhVTy9T1l5/u+OktR7p+HllNL95lzPZq1BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cdf901822a005ef3e42ef916c95dad75301faceb01701fe9fec074bb69ee2ba","last_reissued_at":"2026-07-05T06:44:28.673992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:28.673992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Neural-Network-Based Convex Regularizer for Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Alexis Goujon, Michael Unser, Pakshal Bohra, Sebastian Neumayer, Stanislas Ducotterd","submitted_at":"2022-11-22T18:19:10Z","abstract_excerpt":"The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in reconstruction quality. Unfortunately, these new methods often lack reliability and explainability, and there is a growing interest to address these shortcomings while retaining the boost in performance. In this work, we tackle this issue by revisiting regularizers that are the sum of convex-ridge functions. The gradient of such regularizers is parameterized by a neural network that has a single hidden layer with increasing and learnable activation functions. This neural ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12461","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/2211.12461/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":"2211.12461","created_at":"2026-07-05T06:44:28.674048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12461v3","created_at":"2026-07-05T06:44:28.674048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12461","created_at":"2026-07-05T06:44:28.674048+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTPZAGBCUAC6","created_at":"2026-07-05T06:44:28.674048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTPZAGBCUAC66PSC","created_at":"2026-07-05T06:44:28.674048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTPZAGBC","created_at":"2026-07-05T06:44:28.674048+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/PTPZAGBCUAC66PSC56IWZFO225","json":"https://pith.science/pith/PTPZAGBCUAC66PSC56IWZFO225.json","graph_json":"https://pith.science/api/pith-number/PTPZAGBCUAC66PSC56IWZFO225/graph.json","events_json":"https://pith.science/api/pith-number/PTPZAGBCUAC66PSC56IWZFO225/events.json","paper":"https://pith.science/paper/PTPZAGBC"},"agent_actions":{"view_html":"https://pith.science/pith/PTPZAGBCUAC66PSC56IWZFO225","download_json":"https://pith.science/pith/PTPZAGBCUAC66PSC56IWZFO225.json","view_paper":"https://pith.science/paper/PTPZAGBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12461&json=true","fetch_graph":"https://pith.science/api/pith-number/PTPZAGBCUAC66PSC56IWZFO225/graph.json","fetch_events":"https://pith.science/api/pith-number/PTPZAGBCUAC66PSC56IWZFO225/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTPZAGBCUAC66PSC56IWZFO225/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTPZAGBCUAC66PSC56IWZFO225/action/storage_attestation","attest_author":"https://pith.science/pith/PTPZAGBCUAC66PSC56IWZFO225/action/author_attestation","sign_citation":"https://pith.science/pith/PTPZAGBCUAC66PSC56IWZFO225/action/citation_signature","submit_replication":"https://pith.science/pith/PTPZAGBCUAC66PSC56IWZFO225/action/replication_record"}},"created_at":"2026-07-05T06:44:28.674048+00:00","updated_at":"2026-07-05T06:44:28.674048+00:00"}