{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L4P6DJHG2L3ONKZWOMMY5CNJMJ","short_pith_number":"pith:L4P6DJHG","schema_version":"1.0","canonical_sha256":"5f1fe1a4e6d2f6e6ab3673198e89a962584d5694a63a90d06ca7c11a72099208","source":{"kind":"arxiv","id":"2302.10279","version":2},"attestation_state":"computed","paper":{"title":"Image Reconstruction via Deep Image Prior Subspaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Bangti Jin, Javier Antor\\'an, Johannes Leuschner, Jos\\'e Miguel Hern\\'andez-Lobato, Riccardo Barbano, \\v{Z}eljko Kereta","submitted_at":"2023-02-20T20:19:36Z","abstract_excerpt":"Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP), naturally fill this gap, but bring a host of new issues: the susceptibility to overfitting due to a lack of robust early stopping strategies and unstable convergence. We present a novel approach to tackle these issues by restricting DIP optimisation to a sparse linear subspace of its parameters, employing a synergy of dimensionality reduction techniques and second "},"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":"2302.10279","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-20T20:19:36Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"0cad6dfa624831f85344aced825a8da85a5c08430ba497832967bbc19b7afbe7","abstract_canon_sha256":"a20c1357ef3b6e71b6c1d0c86aa7c763c1913942c7f3604f4a8ce1b835a6b1eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:28.070479Z","signature_b64":"xCHwVmHmyWN1gUgMvLk8UuLS/Q5G1IPEucs77pYpVY8eOrO6bn3H1S3iERcucNqs3A1tE7kOcjadqjaJiu+uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f1fe1a4e6d2f6e6ab3673198e89a962584d5694a63a90d06ca7c11a72099208","last_reissued_at":"2026-07-05T06:17:28.070055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:28.070055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Reconstruction via Deep Image Prior Subspaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Bangti Jin, Javier Antor\\'an, Johannes Leuschner, Jos\\'e Miguel Hern\\'andez-Lobato, Riccardo Barbano, \\v{Z}eljko Kereta","submitted_at":"2023-02-20T20:19:36Z","abstract_excerpt":"Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP), naturally fill this gap, but bring a host of new issues: the susceptibility to overfitting due to a lack of robust early stopping strategies and unstable convergence. We present a novel approach to tackle these issues by restricting DIP optimisation to a sparse linear subspace of its parameters, employing a synergy of dimensionality reduction techniques and second "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10279","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/2302.10279/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":"2302.10279","created_at":"2026-07-05T06:17:28.070109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10279v2","created_at":"2026-07-05T06:17:28.070109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10279","created_at":"2026-07-05T06:17:28.070109+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4P6DJHG2L3O","created_at":"2026-07-05T06:17:28.070109+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4P6DJHG2L3ONKZW","created_at":"2026-07-05T06:17:28.070109+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4P6DJHG","created_at":"2026-07-05T06:17:28.070109+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ","json":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ.json","graph_json":"https://pith.science/api/pith-number/L4P6DJHG2L3ONKZWOMMY5CNJMJ/graph.json","events_json":"https://pith.science/api/pith-number/L4P6DJHG2L3ONKZWOMMY5CNJMJ/events.json","paper":"https://pith.science/paper/L4P6DJHG"},"agent_actions":{"view_html":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ","download_json":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ.json","view_paper":"https://pith.science/paper/L4P6DJHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10279&json=true","fetch_graph":"https://pith.science/api/pith-number/L4P6DJHG2L3ONKZWOMMY5CNJMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/L4P6DJHG2L3ONKZWOMMY5CNJMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ/action/storage_attestation","attest_author":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ/action/author_attestation","sign_citation":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ/action/citation_signature","submit_replication":"https://pith.science/pith/L4P6DJHG2L3ONKZWOMMY5CNJMJ/action/replication_record"}},"created_at":"2026-07-05T06:17:28.070109+00:00","updated_at":"2026-07-05T06:17:28.070109+00:00"}