{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OP5QTGFMET4GHEUJ73HDU2TICX","short_pith_number":"pith:OP5QTGFM","schema_version":"1.0","canonical_sha256":"73fb0998ac24f8639289fece3a6a6815c7cd4574bb2c75e632330ae7a8c66d29","source":{"kind":"arxiv","id":"1910.10797","version":1},"attestation_state":"computed","paper":{"title":"Low Shot Learning with Untrained Neural Networks for Imaging Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Oscar Leong, Wesam Sakla","submitted_at":"2019-10-23T20:23:22Z","abstract_excerpt":"Employing deep neural networks as natural image priors to solve inverse problems either requires large amounts of data to sufficiently train expressive generative models or can succeed with no data via untrained neural networks. However, very few works have considered how to interpolate between these no- to high-data regimes. In particular, how can one use the availability of a small amount of data (even $5-25$ examples) to one's advantage in solving these inverse problems and can a system's performance increase as the amount of data increases as well? In this work, we consider solving linear "},"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":"1910.10797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-23T20:23:22Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"be1f672e74d8eba9a30482599b52cd9208d26b04ae5963858b151766dcd6458f","abstract_canon_sha256":"cafb62d3c4d4087b8e5bd25fa40eaa2a3a6e9cd5810a9212d57216a1a8dce6de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:35.587887Z","signature_b64":"9h2BvsZezgb+a4q4758jM+yqtb30Uk/mftGp0fIybMMW4WZaMWWD3LdhIZN2gQy6Q6mhSzay9TLh4Q4LbcEWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73fb0998ac24f8639289fece3a6a6815c7cd4574bb2c75e632330ae7a8c66d29","last_reissued_at":"2026-07-05T00:14:35.587477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:35.587477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low Shot Learning with Untrained Neural Networks for Imaging Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Oscar Leong, Wesam Sakla","submitted_at":"2019-10-23T20:23:22Z","abstract_excerpt":"Employing deep neural networks as natural image priors to solve inverse problems either requires large amounts of data to sufficiently train expressive generative models or can succeed with no data via untrained neural networks. However, very few works have considered how to interpolate between these no- to high-data regimes. In particular, how can one use the availability of a small amount of data (even $5-25$ examples) to one's advantage in solving these inverse problems and can a system's performance increase as the amount of data increases as well? In this work, we consider solving linear "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10797","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/1910.10797/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":"1910.10797","created_at":"2026-07-05T00:14:35.587548+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.10797v1","created_at":"2026-07-05T00:14:35.587548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10797","created_at":"2026-07-05T00:14:35.587548+00:00"},{"alias_kind":"pith_short_12","alias_value":"OP5QTGFMET4G","created_at":"2026-07-05T00:14:35.587548+00:00"},{"alias_kind":"pith_short_16","alias_value":"OP5QTGFMET4GHEUJ","created_at":"2026-07-05T00:14:35.587548+00:00"},{"alias_kind":"pith_short_8","alias_value":"OP5QTGFM","created_at":"2026-07-05T00:14:35.587548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18189","citing_title":"Towards Lensless Image Deblurring with Prior-Embedded Implicit Neural Representations in the Low-Data Regime","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX","json":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX.json","graph_json":"https://pith.science/api/pith-number/OP5QTGFMET4GHEUJ73HDU2TICX/graph.json","events_json":"https://pith.science/api/pith-number/OP5QTGFMET4GHEUJ73HDU2TICX/events.json","paper":"https://pith.science/paper/OP5QTGFM"},"agent_actions":{"view_html":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX","download_json":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX.json","view_paper":"https://pith.science/paper/OP5QTGFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.10797&json=true","fetch_graph":"https://pith.science/api/pith-number/OP5QTGFMET4GHEUJ73HDU2TICX/graph.json","fetch_events":"https://pith.science/api/pith-number/OP5QTGFMET4GHEUJ73HDU2TICX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX/action/storage_attestation","attest_author":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX/action/author_attestation","sign_citation":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX/action/citation_signature","submit_replication":"https://pith.science/pith/OP5QTGFMET4GHEUJ73HDU2TICX/action/replication_record"}},"created_at":"2026-07-05T00:14:35.587548+00:00","updated_at":"2026-07-05T00:14:35.587548+00:00"}