{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:O5RCNOMQNAFE6RHKMDPYWSBUDJ","short_pith_number":"pith:O5RCNOMQ","canonical_record":{"source":{"id":"1907.03100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T09:30:51Z","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"b1779f466f16f4abb8eb62f733cc5fdbafd531bc7a5179d2b9d5d639550b6b2b","abstract_canon_sha256":"6f45359820874d6bab4b9204277d1d9c4b09ae8cdb278ecee9015c208b68dd10"},"schema_version":"1.0"},"canonical_sha256":"776226b990680a4f44ea60df8b48341a6f34a03cec2f9a8a0d50c7135e112d50","source":{"kind":"arxiv","id":"1907.03100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.03100","created_at":"2026-05-17T23:41:18Z"},{"alias_kind":"arxiv_version","alias_value":"1907.03100v1","created_at":"2026-05-17T23:41:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03100","created_at":"2026-05-17T23:41:18Z"},{"alias_kind":"pith_short_12","alias_value":"O5RCNOMQNAFE","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"O5RCNOMQNAFE6RHK","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"O5RCNOMQ","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:O5RCNOMQNAFE6RHKMDPYWSBUDJ","target":"record","payload":{"canonical_record":{"source":{"id":"1907.03100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T09:30:51Z","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"b1779f466f16f4abb8eb62f733cc5fdbafd531bc7a5179d2b9d5d639550b6b2b","abstract_canon_sha256":"6f45359820874d6bab4b9204277d1d9c4b09ae8cdb278ecee9015c208b68dd10"},"schema_version":"1.0"},"canonical_sha256":"776226b990680a4f44ea60df8b48341a6f34a03cec2f9a8a0d50c7135e112d50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:18.932632Z","signature_b64":"LamVKnNQu4osy9zg2QbBL/I8q7mXStFpaCC6l3sd80NUax0/xa4cCmu0xN8o+pToj409gL6GBe6pupN59FSiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"776226b990680a4f44ea60df8b48341a6f34a03cec2f9a8a0d50c7135e112d50","last_reissued_at":"2026-05-17T23:41:18.932117Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:18.932117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.03100","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":"2026-05-17T23:41:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S+kKSBx44rM0JfXbsJwg63BIS0kZRxlBT9Nh6bxzPa4fJGjHbuu27RgvyB2/AoKmXwbm1UMJERYk2taPPvoCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:25:45.864848Z"},"content_sha256":"ee1976a26b16589ebe2f495d69f6a3e533938ba42495d44831e7c5de81e1cba9","schema_version":"1.0","event_id":"sha256:ee1976a26b16589ebe2f495d69f6a3e533938ba42495d44831e7c5de81e1cba9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:O5RCNOMQNAFE6RHKMDPYWSBUDJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularizing linear inverse problems with convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Reinhard Heckel","submitted_at":"2019-07-06T09:30:51Z","abstract_excerpt":"Deep convolutional neural networks trained on large datsets have emerged as an intriguing alternative for compressing images and solving inverse problems such as denoising and compressive sensing. However, it has only recently been realized that even without training, convolutional networks can function as concise image models, and thus regularize inverse problems. In this paper, we provide further evidence for this finding by studying variations of convolutional neural networks that map few weight parameters to an image. The networks we consider only consist of convolutional operations, with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03100","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":""},"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":"2026-05-17T23:41:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7H8fLHa3aQHcgkZK2k8Vwc8mRrWEkNvo8XcKhHhzluvn3jZxx+Kq7aZc+u3TtNjVa1NTEm9pYhHGGCW7Ah+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:25:45.865560Z"},"content_sha256":"acd96a0c12d5eb6cb8765fecb674a1c68307a45ec70f0c7039a1a31e3d3c431b","schema_version":"1.0","event_id":"sha256:acd96a0c12d5eb6cb8765fecb674a1c68307a45ec70f0c7039a1a31e3d3c431b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5RCNOMQNAFE6RHKMDPYWSBUDJ/bundle.json","state_url":"https://pith.science/pith/O5RCNOMQNAFE6RHKMDPYWSBUDJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5RCNOMQNAFE6RHKMDPYWSBUDJ/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":"2026-05-25T19:25:45Z","links":{"resolver":"https://pith.science/pith/O5RCNOMQNAFE6RHKMDPYWSBUDJ","bundle":"https://pith.science/pith/O5RCNOMQNAFE6RHKMDPYWSBUDJ/bundle.json","state":"https://pith.science/pith/O5RCNOMQNAFE6RHKMDPYWSBUDJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5RCNOMQNAFE6RHKMDPYWSBUDJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:O5RCNOMQNAFE6RHKMDPYWSBUDJ","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":"6f45359820874d6bab4b9204277d1d9c4b09ae8cdb278ecee9015c208b68dd10","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T09:30:51Z","title_canon_sha256":"b1779f466f16f4abb8eb62f733cc5fdbafd531bc7a5179d2b9d5d639550b6b2b"},"schema_version":"1.0","source":{"id":"1907.03100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.03100","created_at":"2026-05-17T23:41:18Z"},{"alias_kind":"arxiv_version","alias_value":"1907.03100v1","created_at":"2026-05-17T23:41:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03100","created_at":"2026-05-17T23:41:18Z"},{"alias_kind":"pith_short_12","alias_value":"O5RCNOMQNAFE","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"O5RCNOMQNAFE6RHK","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"O5RCNOMQ","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:acd96a0c12d5eb6cb8765fecb674a1c68307a45ec70f0c7039a1a31e3d3c431b","target":"graph","created_at":"2026-05-17T23:41:18Z","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"},"paper":{"abstract_excerpt":"Deep convolutional neural networks trained on large datsets have emerged as an intriguing alternative for compressing images and solving inverse problems such as denoising and compressive sensing. However, it has only recently been realized that even without training, convolutional networks can function as concise image models, and thus regularize inverse problems. In this paper, we provide further evidence for this finding by studying variations of convolutional neural networks that map few weight parameters to an image. The networks we consider only consist of convolutional operations, with ","authors_text":"Reinhard Heckel","cross_cats":["cs.CV","cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T09:30:51Z","title":"Regularizing linear inverse problems with convolutional neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03100","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:ee1976a26b16589ebe2f495d69f6a3e533938ba42495d44831e7c5de81e1cba9","target":"record","created_at":"2026-05-17T23:41:18Z","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":"6f45359820874d6bab4b9204277d1d9c4b09ae8cdb278ecee9015c208b68dd10","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T09:30:51Z","title_canon_sha256":"b1779f466f16f4abb8eb62f733cc5fdbafd531bc7a5179d2b9d5d639550b6b2b"},"schema_version":"1.0","source":{"id":"1907.03100","kind":"arxiv","version":1}},"canonical_sha256":"776226b990680a4f44ea60df8b48341a6f34a03cec2f9a8a0d50c7135e112d50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"776226b990680a4f44ea60df8b48341a6f34a03cec2f9a8a0d50c7135e112d50","first_computed_at":"2026-05-17T23:41:18.932117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:18.932117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LamVKnNQu4osy9zg2QbBL/I8q7mXStFpaCC6l3sd80NUax0/xa4cCmu0xN8o+pToj409gL6GBe6pupN59FSiBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:18.932632Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.03100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee1976a26b16589ebe2f495d69f6a3e533938ba42495d44831e7c5de81e1cba9","sha256:acd96a0c12d5eb6cb8765fecb674a1c68307a45ec70f0c7039a1a31e3d3c431b"],"state_sha256":"98ccc0c9570dafe97da12f69cacbf11eb8402f01170538770a596745977d0008"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"siHlUk5eOZ7+uovmh1nYgxwiDPL6lhr454iQ8S5jkUqIHIn0ZIghS097yA4YPY6d1SZt7M4NuJ2yO7PiHkQSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:25:45.870378Z","bundle_sha256":"e33d21f0484b70bb6f27d6808adde784a3f9ac460082587ba5a67eb30fd4337f"}}