{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EY7F5U2BCRJZFC5ZWF7A7UQC43","short_pith_number":"pith:EY7F5U2B","schema_version":"1.0","canonical_sha256":"263e5ed3411453928bb9b17e0fd202e6e8c402c0d5821fe5235a65cfc042b847","source":{"kind":"arxiv","id":"1711.10925","version":4},"attestation_state":"computed","paper":{"title":"Deep Image Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Dmitry Ulyanov, Victor Lempitsky","submitted_at":"2017-11-29T15:50:05Z","abstract_excerpt":"Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning. In order to do so, we show that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, super-resolution, a"},"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":"1711.10925","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-29T15:50:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"15c41666801f24d50dcd6517917dc776b2d7b9dc51aebc9d594932e0090d4e0f","abstract_canon_sha256":"efa08482207b03747f6b2fc38c19349669c17dae883ffacb6b94acf384340c17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:17.275839Z","signature_b64":"lhAfVXs4SR6M11430i09/NtmJWQpCHjqnS80r6jRzwpFr7fbuSNK83gJKmMXjgqupK4FOnyYjlZirEUSzFTvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"263e5ed3411453928bb9b17e0fd202e6e8c402c0d5821fe5235a65cfc042b847","last_reissued_at":"2026-07-05T01:03:17.275449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:17.275449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Image Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Dmitry Ulyanov, Victor Lempitsky","submitted_at":"2017-11-29T15:50:05Z","abstract_excerpt":"Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning. In order to do so, we show that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, super-resolution, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10925","kind":"arxiv","version":4},"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/1711.10925/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":"1711.10925","created_at":"2026-07-05T01:03:17.275508+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10925v4","created_at":"2026-07-05T01:03:17.275508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10925","created_at":"2026-07-05T01:03:17.275508+00:00"},{"alias_kind":"pith_short_12","alias_value":"EY7F5U2BCRJZ","created_at":"2026-07-05T01:03:17.275508+00:00"},{"alias_kind":"pith_short_16","alias_value":"EY7F5U2BCRJZFC5Z","created_at":"2026-07-05T01:03:17.275508+00:00"},{"alias_kind":"pith_short_8","alias_value":"EY7F5U2B","created_at":"2026-07-05T01:03:17.275508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08281","citing_title":"Enhancing the KidSat Model: Integrating Geographical Encoding and Data Quality Assessment for Childhood Poverty Prediction","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2502.21292","citing_title":"Bilevel Optimized Implicit Neural Representation for Scan-Specific Accelerated MRI Reconstruction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03572","citing_title":"Physics-Informed Untrained Learning for RGB-Guided Superresolution Single-Pixel Hyperspectral Imaging","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43","json":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43.json","graph_json":"https://pith.science/api/pith-number/EY7F5U2BCRJZFC5ZWF7A7UQC43/graph.json","events_json":"https://pith.science/api/pith-number/EY7F5U2BCRJZFC5ZWF7A7UQC43/events.json","paper":"https://pith.science/paper/EY7F5U2B"},"agent_actions":{"view_html":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43","download_json":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43.json","view_paper":"https://pith.science/paper/EY7F5U2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10925&json=true","fetch_graph":"https://pith.science/api/pith-number/EY7F5U2BCRJZFC5ZWF7A7UQC43/graph.json","fetch_events":"https://pith.science/api/pith-number/EY7F5U2BCRJZFC5ZWF7A7UQC43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43/action/storage_attestation","attest_author":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43/action/author_attestation","sign_citation":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43/action/citation_signature","submit_replication":"https://pith.science/pith/EY7F5U2BCRJZFC5ZWF7A7UQC43/action/replication_record"}},"created_at":"2026-07-05T01:03:17.275508+00:00","updated_at":"2026-07-05T01:03:17.275508+00:00"}