{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G7U2WOXW7VDRLQOUDH7B42WHJX","short_pith_number":"pith:G7U2WOXW","canonical_record":{"source":{"id":"2003.05417","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-03-11T17:09:12Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4d46a4449910c30e6352612115389be7b108c9d9e608463502fe34a134085871","abstract_canon_sha256":"c0881f1336e7547041baeedcec256a7800b269af39afa71fc7b3a5d1e047a589"},"schema_version":"1.0"},"canonical_sha256":"37e9ab3af6fd4715c1d419fe1e6ac74dca60a97133ae7bb1e5caa880f576226b","source":{"kind":"arxiv","id":"2003.05417","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.05417","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"2003.05417v2","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05417","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"G7U2WOXW7VDR","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"pith_short_16","alias_value":"G7U2WOXW7VDRLQOU","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"pith_short_8","alias_value":"G7U2WOXW","created_at":"2026-07-05T01:14:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G7U2WOXW7VDRLQOUDH7B42WHJX","target":"record","payload":{"canonical_record":{"source":{"id":"2003.05417","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-03-11T17:09:12Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4d46a4449910c30e6352612115389be7b108c9d9e608463502fe34a134085871","abstract_canon_sha256":"c0881f1336e7547041baeedcec256a7800b269af39afa71fc7b3a5d1e047a589"},"schema_version":"1.0"},"canonical_sha256":"37e9ab3af6fd4715c1d419fe1e6ac74dca60a97133ae7bb1e5caa880f576226b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:41.785650Z","signature_b64":"dv6TO9/WVzoDqsNMwC/IgthbBRCotEn9Val6+piY2MP2ng6BThIwvRJCKvOfPVoCZW2NpUx8ndwlK9MNnO9HAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37e9ab3af6fd4715c1d419fe1e6ac74dca60a97133ae7bb1e5caa880f576226b","last_reissued_at":"2026-07-05T01:14:41.785221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:41.785221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.05417","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":"2026-07-05T01:14:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UPyvr2mntXxMMiO8E6T0p1tOWpfDzMvjANdZ6obSbxsDlbFkxEQ5HYPCUvZ9/sTwkpVpJt3HnoZOHonK1WADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:32:39.519114Z"},"content_sha256":"97f004f621b913e55a05e1200732dcb492114687f7aab765e6d0952d22230d00","schema_version":"1.0","event_id":"sha256:97f004f621b913e55a05e1200732dcb492114687f7aab765e6d0952d22230d00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G7U2WOXW7VDRLQOUDH7B42WHJX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BP-DIP: A Backprojection based Deep Image Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"eess.IV","authors_text":"Jenny Zukerman, Raja Giryes, Tom Tirer","submitted_at":"2020-03-11T17:09:12Z","abstract_excerpt":"Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used in training mismatches the one in test time. In addition, most deep learning methods require vast amounts of training data, which are not accessible in many applications. To mitigate these disadvantages, we propose to combine two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05417","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.05417/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":"2026-07-05T01:14:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mpZCE/XwHtWMMc60c3MJCulBjzi4NimeVtr5PH5vepD0Moi02MxssS8wWjExWoJaapgmqOWN4ZTptSP6+r3ACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:32:39.520116Z"},"content_sha256":"333263a8d54b1e36ad7dc9180854d36fa851d1bfe622f849dbf9d07e037faf30","schema_version":"1.0","event_id":"sha256:333263a8d54b1e36ad7dc9180854d36fa851d1bfe622f849dbf9d07e037faf30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7U2WOXW7VDRLQOUDH7B42WHJX/bundle.json","state_url":"https://pith.science/pith/G7U2WOXW7VDRLQOUDH7B42WHJX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7U2WOXW7VDRLQOUDH7B42WHJX/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":"2026-08-06T16:32:39Z","links":{"resolver":"https://pith.science/pith/G7U2WOXW7VDRLQOUDH7B42WHJX","bundle":"https://pith.science/pith/G7U2WOXW7VDRLQOUDH7B42WHJX/bundle.json","state":"https://pith.science/pith/G7U2WOXW7VDRLQOUDH7B42WHJX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7U2WOXW7VDRLQOUDH7B42WHJX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G7U2WOXW7VDRLQOUDH7B42WHJX","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":"c0881f1336e7547041baeedcec256a7800b269af39afa71fc7b3a5d1e047a589","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-03-11T17:09:12Z","title_canon_sha256":"4d46a4449910c30e6352612115389be7b108c9d9e608463502fe34a134085871"},"schema_version":"1.0","source":{"id":"2003.05417","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.05417","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"2003.05417v2","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05417","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"G7U2WOXW7VDR","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"pith_short_16","alias_value":"G7U2WOXW7VDRLQOU","created_at":"2026-07-05T01:14:41Z"},{"alias_kind":"pith_short_8","alias_value":"G7U2WOXW","created_at":"2026-07-05T01:14:41Z"}],"graph_snapshots":[{"event_id":"sha256:333263a8d54b1e36ad7dc9180854d36fa851d1bfe622f849dbf9d07e037faf30","target":"graph","created_at":"2026-07-05T01:14:41Z","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/2003.05417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used in training mismatches the one in test time. In addition, most deep learning methods require vast amounts of training data, which are not accessible in many applications. To mitigate these disadvantages, we propose to combine two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test t","authors_text":"Jenny Zukerman, Raja Giryes, Tom Tirer","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-03-11T17:09:12Z","title":"BP-DIP: A Backprojection based Deep Image Prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05417","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":"sha256:97f004f621b913e55a05e1200732dcb492114687f7aab765e6d0952d22230d00","target":"record","created_at":"2026-07-05T01:14:41Z","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":"c0881f1336e7547041baeedcec256a7800b269af39afa71fc7b3a5d1e047a589","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-03-11T17:09:12Z","title_canon_sha256":"4d46a4449910c30e6352612115389be7b108c9d9e608463502fe34a134085871"},"schema_version":"1.0","source":{"id":"2003.05417","kind":"arxiv","version":2}},"canonical_sha256":"37e9ab3af6fd4715c1d419fe1e6ac74dca60a97133ae7bb1e5caa880f576226b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37e9ab3af6fd4715c1d419fe1e6ac74dca60a97133ae7bb1e5caa880f576226b","first_computed_at":"2026-07-05T01:14:41.785221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:14:41.785221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dv6TO9/WVzoDqsNMwC/IgthbBRCotEn9Val6+piY2MP2ng6BThIwvRJCKvOfPVoCZW2NpUx8ndwlK9MNnO9HAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:14:41.785650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.05417","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97f004f621b913e55a05e1200732dcb492114687f7aab765e6d0952d22230d00","sha256:333263a8d54b1e36ad7dc9180854d36fa851d1bfe622f849dbf9d07e037faf30"],"state_sha256":"351f3462f1c3084d26871a70e669f97eedbf8f5c49ae0f9e743018ccede3f1e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSGusbVhYWiGkrFuaCtdcmAnAs3r/DkT4VaDAx6WyUjwDymX1i09SxKn82rgrZnamQ94BXeJfXqs2Vf2dDmHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:32:39.530931Z","bundle_sha256":"f2367d3b976a601ef3b56c066013bf13b000f8918ed21871d2f17e5de31da60c"}}