{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RFGYRMEC27JQJ24C3AOP6OAY2N","short_pith_number":"pith:RFGYRMEC","schema_version":"1.0","canonical_sha256":"894d88b082d7d304eb82d81cff3818d366bb0d9cf56123c6c2fbbd877bc24fcb","source":{"kind":"arxiv","id":"2505.11720","version":1},"attestation_state":"computed","paper":{"title":"UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Ismail R. Alkhouri, Qing Qu, Saiprasad Ravishankar, Shijun Liang, Siddhant Gautam","submitted_at":"2025-05-16T22:05:28Z","abstract_excerpt":"Recent advances in data-centric deep generative models have led to significant progress in solving inverse imaging problems. However, these models (e.g., diffusion models (DMs)) typically require large amounts of fully sampled (clean) training data, which is often impractical in medical and scientific settings such as dynamic imaging.\n  On the other hand, training-data-free approaches like the Deep Image Prior (DIP) do not require clean ground-truth images but suffer from noise overfitting and can be computationally expensive as the network parameters need to be optimized for each measurement "},"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":"2505.11720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T22:05:28Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"7d7c49e8eb43b863939cfa08e7830dda50b5e1f5612869de1e9a5d0b44ff9813","abstract_canon_sha256":"20d5ef799c8902470c2159a0d51a507310127b8a9177b06784fcf06fc9ef2baf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:25.812045Z","signature_b64":"jEUCdh08kk7A7ErNqP6sw3cjMvo92gPAcSuNWh3WdNSKICigb9CAL49qelKYH3q5sHe+UQ7IX33WEmIpoap0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"894d88b082d7d304eb82d81cff3818d366bb0d9cf56123c6c2fbbd877bc24fcb","last_reissued_at":"2026-07-05T11:04:25.811531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:25.811531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Ismail R. Alkhouri, Qing Qu, Saiprasad Ravishankar, Shijun Liang, Siddhant Gautam","submitted_at":"2025-05-16T22:05:28Z","abstract_excerpt":"Recent advances in data-centric deep generative models have led to significant progress in solving inverse imaging problems. However, these models (e.g., diffusion models (DMs)) typically require large amounts of fully sampled (clean) training data, which is often impractical in medical and scientific settings such as dynamic imaging.\n  On the other hand, training-data-free approaches like the Deep Image Prior (DIP) do not require clean ground-truth images but suffer from noise overfitting and can be computationally expensive as the network parameters need to be optimized for each measurement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11720","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.11720/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":"2505.11720","created_at":"2026-07-05T11:04:25.811593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11720v1","created_at":"2026-07-05T11:04:25.811593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11720","created_at":"2026-07-05T11:04:25.811593+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFGYRMEC27JQ","created_at":"2026-07-05T11:04:25.811593+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFGYRMEC27JQJ24C","created_at":"2026-07-05T11:04:25.811593+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFGYRMEC","created_at":"2026-07-05T11:04:25.811593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.16520","citing_title":"Saving Foundation Flow-Matching Priors for Inverse Problems","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N","json":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N.json","graph_json":"https://pith.science/api/pith-number/RFGYRMEC27JQJ24C3AOP6OAY2N/graph.json","events_json":"https://pith.science/api/pith-number/RFGYRMEC27JQJ24C3AOP6OAY2N/events.json","paper":"https://pith.science/paper/RFGYRMEC"},"agent_actions":{"view_html":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N","download_json":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N.json","view_paper":"https://pith.science/paper/RFGYRMEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11720&json=true","fetch_graph":"https://pith.science/api/pith-number/RFGYRMEC27JQJ24C3AOP6OAY2N/graph.json","fetch_events":"https://pith.science/api/pith-number/RFGYRMEC27JQJ24C3AOP6OAY2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N/action/storage_attestation","attest_author":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N/action/author_attestation","sign_citation":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N/action/citation_signature","submit_replication":"https://pith.science/pith/RFGYRMEC27JQJ24C3AOP6OAY2N/action/replication_record"}},"created_at":"2026-07-05T11:04:25.811593+00:00","updated_at":"2026-07-05T11:04:25.811593+00:00"}