{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G45JBDNEJLDK7RXSIW55HPGHPD","short_pith_number":"pith:G45JBDNE","canonical_record":{"source":{"id":"2012.05169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T16:57:16Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"b9c2dc6d3100d747fe4cdb9fbf716164b97e33be3f01fba2bb555d781d28ad0a","abstract_canon_sha256":"1fe21b1d8c01550517134dcc4290674aad56cfdd3c86c30c2e11b133ac96514e"},"schema_version":"1.0"},"canonical_sha256":"373a908da44ac6afc6f245bbd3bcc778ee7344e726b411440051b79d69c6add2","source":{"kind":"arxiv","id":"2012.05169","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05169","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05169v1","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05169","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"pith_short_12","alias_value":"G45JBDNEJLDK","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"pith_short_16","alias_value":"G45JBDNEJLDK7RXS","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"pith_short_8","alias_value":"G45JBDNE","created_at":"2026-07-05T01:58:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G45JBDNEJLDK7RXSIW55HPGHPD","target":"record","payload":{"canonical_record":{"source":{"id":"2012.05169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T16:57:16Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"b9c2dc6d3100d747fe4cdb9fbf716164b97e33be3f01fba2bb555d781d28ad0a","abstract_canon_sha256":"1fe21b1d8c01550517134dcc4290674aad56cfdd3c86c30c2e11b133ac96514e"},"schema_version":"1.0"},"canonical_sha256":"373a908da44ac6afc6f245bbd3bcc778ee7344e726b411440051b79d69c6add2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:19.559065Z","signature_b64":"THc7xYkxNk+m8c319q/ExQdKpN1uPB5Sbr7Ryuz+kCyiG9mrAC1uAvZkScmsXHeuW0DnYQv9cKNESvLLc6ElBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"373a908da44ac6afc6f245bbd3bcc778ee7344e726b411440051b79d69c6add2","last_reissued_at":"2026-07-05T01:58:19.558676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:19.558676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.05169","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:58:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M4MeOK8dZUobqN/DuVb0mYIfD/+uewnCViN2xxNrR2rPyzhYnKUY5c67AzJGm88iKzKKvPNJiH0UtgO/aQZ4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:54:39.323217Z"},"content_sha256":"b156f1457390f97027822523f25e8046b068cd8ffc09eed932959e0456814389","schema_version":"1.0","event_id":"sha256:b156f1457390f97027822523f25e8046b068cd8ffc09eed932959e0456814389"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G45JBDNEJLDK7RXSIW55HPGHPD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convex Regularization Behind Neural Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arda Sahiner, Batu Ozturkler, John Pauly, Mert Pilanci, Morteza Mardani","submitted_at":"2020-12-09T16:57:16Z","abstract_excerpt":"Neural networks have shown tremendous potential for reconstructing high-resolution images in inverse problems. The non-convex and opaque nature of neural networks, however, hinders their utility in sensitive applications such as medical imaging. To cope with this challenge, this paper advocates a convex duality framework that makes a two-layer fully-convolutional ReLU denoising network amenable to convex optimization. The convex dual network not only offers the optimum training with convex solvers, but also facilitates interpreting training and prediction. In particular, it implies training ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05169","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/2012.05169/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:58:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TfrQqbLwkk7UhdPPlnXs68P0GUrUVTSemnO0ghl+z23VhbCfXbQeZN0CHIsUeeBDJzFINkDxIjGSZp/SLw5zCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:54:39.323708Z"},"content_sha256":"6e9d8d51daaa820c1e3ac91799e3cd9cec6cfbf3781e6a4d78df3fc70d91ec67","schema_version":"1.0","event_id":"sha256:6e9d8d51daaa820c1e3ac91799e3cd9cec6cfbf3781e6a4d78df3fc70d91ec67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G45JBDNEJLDK7RXSIW55HPGHPD/bundle.json","state_url":"https://pith.science/pith/G45JBDNEJLDK7RXSIW55HPGHPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G45JBDNEJLDK7RXSIW55HPGHPD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T11:54:39Z","links":{"resolver":"https://pith.science/pith/G45JBDNEJLDK7RXSIW55HPGHPD","bundle":"https://pith.science/pith/G45JBDNEJLDK7RXSIW55HPGHPD/bundle.json","state":"https://pith.science/pith/G45JBDNEJLDK7RXSIW55HPGHPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G45JBDNEJLDK7RXSIW55HPGHPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G45JBDNEJLDK7RXSIW55HPGHPD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1fe21b1d8c01550517134dcc4290674aad56cfdd3c86c30c2e11b133ac96514e","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T16:57:16Z","title_canon_sha256":"b9c2dc6d3100d747fe4cdb9fbf716164b97e33be3f01fba2bb555d781d28ad0a"},"schema_version":"1.0","source":{"id":"2012.05169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05169","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05169v1","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05169","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"pith_short_12","alias_value":"G45JBDNEJLDK","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"pith_short_16","alias_value":"G45JBDNEJLDK7RXS","created_at":"2026-07-05T01:58:19Z"},{"alias_kind":"pith_short_8","alias_value":"G45JBDNE","created_at":"2026-07-05T01:58:19Z"}],"graph_snapshots":[{"event_id":"sha256:6e9d8d51daaa820c1e3ac91799e3cd9cec6cfbf3781e6a4d78df3fc70d91ec67","target":"graph","created_at":"2026-07-05T01:58:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.05169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks have shown tremendous potential for reconstructing high-resolution images in inverse problems. The non-convex and opaque nature of neural networks, however, hinders their utility in sensitive applications such as medical imaging. To cope with this challenge, this paper advocates a convex duality framework that makes a two-layer fully-convolutional ReLU denoising network amenable to convex optimization. The convex dual network not only offers the optimum training with convex solvers, but also facilitates interpreting training and prediction. In particular, it implies training ne","authors_text":"Arda Sahiner, Batu Ozturkler, John Pauly, Mert Pilanci, Morteza Mardani","cross_cats":["cs.CV","eess.IV","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T16:57:16Z","title":"Convex Regularization Behind Neural Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05169","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b156f1457390f97027822523f25e8046b068cd8ffc09eed932959e0456814389","target":"record","created_at":"2026-07-05T01:58:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1fe21b1d8c01550517134dcc4290674aad56cfdd3c86c30c2e11b133ac96514e","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T16:57:16Z","title_canon_sha256":"b9c2dc6d3100d747fe4cdb9fbf716164b97e33be3f01fba2bb555d781d28ad0a"},"schema_version":"1.0","source":{"id":"2012.05169","kind":"arxiv","version":1}},"canonical_sha256":"373a908da44ac6afc6f245bbd3bcc778ee7344e726b411440051b79d69c6add2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"373a908da44ac6afc6f245bbd3bcc778ee7344e726b411440051b79d69c6add2","first_computed_at":"2026-07-05T01:58:19.558676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:19.558676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"THc7xYkxNk+m8c319q/ExQdKpN1uPB5Sbr7Ryuz+kCyiG9mrAC1uAvZkScmsXHeuW0DnYQv9cKNESvLLc6ElBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:19.559065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b156f1457390f97027822523f25e8046b068cd8ffc09eed932959e0456814389","sha256:6e9d8d51daaa820c1e3ac91799e3cd9cec6cfbf3781e6a4d78df3fc70d91ec67"],"state_sha256":"16d6398c940a9e68c5fe7302d4fa265bc6ba916fbbda9160a0b3698c977730ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bw7YVp/LcX396FIG817NBUUW38krr8f0uE/5KgfvtVBfvBgCtoIeTS0ZsNpufn3feCa+dP59rGSrXCMXu6SxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:54:39.327048Z","bundle_sha256":"e6eefd76ad68550703c877aa1bd70af21f209864f3600cef357ec36970dcb31b"}}