{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2G5MI7WLFHBYUBZZ22ESDP3OTH","short_pith_number":"pith:2G5MI7WL","canonical_record":{"source":{"id":"1810.03982","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T20:07:07Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7e2b9035334fcd50803fb771c75277e0c4e059b64b975df822be8dde1a0a6638","abstract_canon_sha256":"c296bbbbc38e018a2b5e68fda20f8fb363ec50fee3e87f2e7e999eca73c98b54"},"schema_version":"1.0"},"canonical_sha256":"d1bac47ecb29c38a0739d68921bf6e99c980215b48a5d7fd531c9e3ab6263429","source":{"kind":"arxiv","id":"1810.03982","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03982","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03982v2","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03982","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"2G5MI7WLFHBY","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2G5MI7WLFHBYUBZZ","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2G5MI7WL","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2G5MI7WLFHBYUBZZ22ESDP3OTH","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03982","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T20:07:07Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7e2b9035334fcd50803fb771c75277e0c4e059b64b975df822be8dde1a0a6638","abstract_canon_sha256":"c296bbbbc38e018a2b5e68fda20f8fb363ec50fee3e87f2e7e999eca73c98b54"},"schema_version":"1.0"},"canonical_sha256":"d1bac47ecb29c38a0739d68921bf6e99c980215b48a5d7fd531c9e3ab6263429","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:39.317892Z","signature_b64":"a2ZLh/sTFVjrYKxNUxbbYOJ6DrhAwyaN7pt0WgNlZYGrIxNpg+gpzxP+ju9qGvYWYkYFEB/lv8GqvwgnD+PVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1bac47ecb29c38a0739d68921bf6e99c980215b48a5d7fd531c9e3ab6263429","last_reissued_at":"2026-05-17T23:51:39.317228Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:39.317228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03982","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qufqsYSbz7d1AdlXI2r6yZDzk1GuogzL+K/Dbvz5Q7nwb3yCMj0/6cuxhbqP58CS+rckz35RZBP/apPKXSc0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T21:47:58.630193Z"},"content_sha256":"5b9b03a895d342def338fef7b93393bcbdae3e730e94adb3fcdc85848406c55a","schema_version":"1.0","event_id":"sha256:5b9b03a895d342def338fef7b93393bcbdae3e730e94adb3fcdc85848406c55a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2G5MI7WLFHBYUBZZ22ESDP3OTH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Paul Hand, Reinhard Heckel","submitted_at":"2018-10-02T20:07:07Z","abstract_excerpt":"Deep neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements. This success can be attributed in part to their ability to represent and generate natural images well. Contrary to classical tools such as wavelets, image-generating deep neural networks have a large number of parameters---typically a multiple of their output dimension---and need to be trained on large datasets. In this paper, we propose an untrained simple i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03982","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":""},"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":"2026-05-17T23:51:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ji3Q/G3nzjChXTs5Sp9D3faqXnaFM2FCpLpGNw4uU/orKGGMszO4nWj0ickHNNH6qgQQ1k/urrkGS9eb+nJpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T21:47:58.630926Z"},"content_sha256":"5c3bc5271dfc462f8cf76319acd3b87861753a46a77e02a5174941fc733dce38","schema_version":"1.0","event_id":"sha256:5c3bc5271dfc462f8cf76319acd3b87861753a46a77e02a5174941fc733dce38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2G5MI7WLFHBYUBZZ22ESDP3OTH/bundle.json","state_url":"https://pith.science/pith/2G5MI7WLFHBYUBZZ22ESDP3OTH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2G5MI7WLFHBYUBZZ22ESDP3OTH/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":"2026-05-23T21:47:58Z","links":{"resolver":"https://pith.science/pith/2G5MI7WLFHBYUBZZ22ESDP3OTH","bundle":"https://pith.science/pith/2G5MI7WLFHBYUBZZ22ESDP3OTH/bundle.json","state":"https://pith.science/pith/2G5MI7WLFHBYUBZZ22ESDP3OTH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2G5MI7WLFHBYUBZZ22ESDP3OTH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2G5MI7WLFHBYUBZZ22ESDP3OTH","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":"c296bbbbc38e018a2b5e68fda20f8fb363ec50fee3e87f2e7e999eca73c98b54","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T20:07:07Z","title_canon_sha256":"7e2b9035334fcd50803fb771c75277e0c4e059b64b975df822be8dde1a0a6638"},"schema_version":"1.0","source":{"id":"1810.03982","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03982","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03982v2","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03982","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"2G5MI7WLFHBY","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2G5MI7WLFHBYUBZZ","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2G5MI7WL","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:5c3bc5271dfc462f8cf76319acd3b87861753a46a77e02a5174941fc733dce38","target":"graph","created_at":"2026-05-17T23:51:39Z","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 neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements. This success can be attributed in part to their ability to represent and generate natural images well. Contrary to classical tools such as wavelets, image-generating deep neural networks have a large number of parameters---typically a multiple of their output dimension---and need to be trained on large datasets. In this paper, we propose an untrained simple i","authors_text":"Paul Hand, Reinhard Heckel","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T20:07:07Z","title":"Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03982","kind":"arxiv","version":2},"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":"sha256:5b9b03a895d342def338fef7b93393bcbdae3e730e94adb3fcdc85848406c55a","target":"record","created_at":"2026-05-17T23:51:39Z","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":"c296bbbbc38e018a2b5e68fda20f8fb363ec50fee3e87f2e7e999eca73c98b54","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T20:07:07Z","title_canon_sha256":"7e2b9035334fcd50803fb771c75277e0c4e059b64b975df822be8dde1a0a6638"},"schema_version":"1.0","source":{"id":"1810.03982","kind":"arxiv","version":2}},"canonical_sha256":"d1bac47ecb29c38a0739d68921bf6e99c980215b48a5d7fd531c9e3ab6263429","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1bac47ecb29c38a0739d68921bf6e99c980215b48a5d7fd531c9e3ab6263429","first_computed_at":"2026-05-17T23:51:39.317228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:39.317228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a2ZLh/sTFVjrYKxNUxbbYOJ6DrhAwyaN7pt0WgNlZYGrIxNpg+gpzxP+ju9qGvYWYkYFEB/lv8GqvwgnD+PVAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:39.317892Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03982","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b9b03a895d342def338fef7b93393bcbdae3e730e94adb3fcdc85848406c55a","sha256:5c3bc5271dfc462f8cf76319acd3b87861753a46a77e02a5174941fc733dce38"],"state_sha256":"284abacdf37e9c92cb702aeb9dc7e519e2a50736e83f4f4810ce90c1fe9714e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F9wxKJjmtTXrr+316q6q1afu8maxi7SX17M3gIVQ5hOnn2oWmQf/DUyAv8wmRTgBGH024FT6j6XRC5gpQjkIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T21:47:58.634613Z","bundle_sha256":"6cc6110e8fe03f623c6153c7e95c4b4a1f02f4a3021ca504f35e960ae05305ca"}}