{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5NUUA7Q6SHQXFMZMDMYHTLMN2C","short_pith_number":"pith:5NUUA7Q6","schema_version":"1.0","canonical_sha256":"eb69407e1e91e172b32c1b3079ad8dd08ca4f9ded936d1ce3b3bf587c8a0d93e","source":{"kind":"arxiv","id":"2203.04382","version":1},"attestation_state":"computed","paper":{"title":"Regularized Training of Intermediate Layers for Generative Models for Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Jorio Cocola, Paul Hand, Sean Gunn","submitted_at":"2022-03-08T20:30:49Z","abstract_excerpt":"Generative Adversarial Networks (GANs) have been shown to be powerful and flexible priors when solving inverse problems. One challenge of using them is overcoming representation error, the fundamental limitation of the network in representing any particular signal. Recently, multiple proposed inversion algorithms reduce representation error by optimizing over intermediate layer representations. These methods are typically applied to generative models that were trained agnostic of the downstream inversion algorithm. In our work, we introduce a principle that if a generative model is intended fo"},"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":"2203.04382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-08T20:30:49Z","cross_cats_sorted":["cs.CV","eess.IV"],"title_canon_sha256":"a78f8fac735d27af5ebc67d865b6096cde0d66c24564148d27839d4d9787d002","abstract_canon_sha256":"57095e04975e824338176396ec0d541dbe93e10142321b4ebb65db10c523d212"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:12.829865Z","signature_b64":"vOB7gwyuowDRdSOC5TRTNqHXKG6SQ59HwJO0M668T1GoLL8WCSLgmzz10YmreHpiraEKm+E6NMhy/x/w5lb/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb69407e1e91e172b32c1b3079ad8dd08ca4f9ded936d1ce3b3bf587c8a0d93e","last_reissued_at":"2026-07-05T04:13:12.829331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:12.829331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularized Training of Intermediate Layers for Generative Models for Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Jorio Cocola, Paul Hand, Sean Gunn","submitted_at":"2022-03-08T20:30:49Z","abstract_excerpt":"Generative Adversarial Networks (GANs) have been shown to be powerful and flexible priors when solving inverse problems. One challenge of using them is overcoming representation error, the fundamental limitation of the network in representing any particular signal. Recently, multiple proposed inversion algorithms reduce representation error by optimizing over intermediate layer representations. These methods are typically applied to generative models that were trained agnostic of the downstream inversion algorithm. In our work, we introduce a principle that if a generative model is intended fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04382","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/2203.04382/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":"2203.04382","created_at":"2026-07-05T04:13:12.829432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.04382v1","created_at":"2026-07-05T04:13:12.829432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04382","created_at":"2026-07-05T04:13:12.829432+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NUUA7Q6SHQX","created_at":"2026-07-05T04:13:12.829432+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NUUA7Q6SHQXFMZM","created_at":"2026-07-05T04:13:12.829432+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NUUA7Q6","created_at":"2026-07-05T04:13:12.829432+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/5NUUA7Q6SHQXFMZMDMYHTLMN2C","json":"https://pith.science/pith/5NUUA7Q6SHQXFMZMDMYHTLMN2C.json","graph_json":"https://pith.science/api/pith-number/5NUUA7Q6SHQXFMZMDMYHTLMN2C/graph.json","events_json":"https://pith.science/api/pith-number/5NUUA7Q6SHQXFMZMDMYHTLMN2C/events.json","paper":"https://pith.science/paper/5NUUA7Q6"},"agent_actions":{"view_html":"https://pith.science/pith/5NUUA7Q6SHQXFMZMDMYHTLMN2C","download_json":"https://pith.science/pith/5NUUA7Q6SHQXFMZMDMYHTLMN2C.json","view_paper":"https://pith.science/paper/5NUUA7Q6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.04382&json=true","fetch_graph":"https://pith.science/api/pith-number/5NUUA7Q6SHQXFMZMDMYHTLMN2C/graph.json","fetch_events":"https://pith.science/api/pith-number/5NUUA7Q6SHQXFMZMDMYHTLMN2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NUUA7Q6SHQXFMZMDMYHTLMN2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NUUA7Q6SHQXFMZMDMYHTLMN2C/action/storage_attestation","attest_author":"https://pith.science/pith/5NUUA7Q6SHQXFMZMDMYHTLMN2C/action/author_attestation","sign_citation":"https://pith.science/pith/5NUUA7Q6SHQXFMZMDMYHTLMN2C/action/citation_signature","submit_replication":"https://pith.science/pith/5NUUA7Q6SHQXFMZMDMYHTLMN2C/action/replication_record"}},"created_at":"2026-07-05T04:13:12.829432+00:00","updated_at":"2026-07-05T04:13:12.829432+00:00"}