{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GCOFV2WPWLTXMCVFDOQBDWYX25","short_pith_number":"pith:GCOFV2WP","schema_version":"1.0","canonical_sha256":"309c5aeacfb2e7760aa51ba011db17d74042895765506a4428759bb2de33d1ea","source":{"kind":"arxiv","id":"2505.15777","version":1},"attestation_state":"computed","paper":{"title":"Projection-Based Correction for Enhancing Deep Inverse Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Jorge Bacca","submitted_at":"2025-05-21T17:28:14Z","abstract_excerpt":"Deep learning-based models have demonstrated remarkable success in solving illposed inverse problems; however, many fail to strictly adhere to the physical constraints imposed by the measurement process. In this work, we introduce a projection-based correction method to enhance the inference of deep inverse networks by ensuring consistency with the forward model. Specifically, given an initial estimate from a learned reconstruction network, we apply a projection step that constrains the solution to lie within the valid solution space of the inverse problem. We theoretically demonstrate that if"},"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":"2505.15777","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T17:28:14Z","cross_cats_sorted":["cs.CV","physics.comp-ph"],"title_canon_sha256":"3d6c9bdcb13ce140e1058d65e6178cd3035538f43f9b5644a62a3122fd82512a","abstract_canon_sha256":"48d9f34ac82179df507d7124adec7518cf495ad71b5489cf6e219c14990e8d16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:57.790026Z","signature_b64":"RjF/QEp14Pvi/1vGzSFfkTlUI3KT9JfyhZzfaWbdLXLfE2GK0Di+vtX9FOUvXPzVujoxkK8uHaI0w0189fwbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"309c5aeacfb2e7760aa51ba011db17d74042895765506a4428759bb2de33d1ea","last_reissued_at":"2026-07-05T11:06:57.789578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:57.789578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Projection-Based Correction for Enhancing Deep Inverse Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Jorge Bacca","submitted_at":"2025-05-21T17:28:14Z","abstract_excerpt":"Deep learning-based models have demonstrated remarkable success in solving illposed inverse problems; however, many fail to strictly adhere to the physical constraints imposed by the measurement process. In this work, we introduce a projection-based correction method to enhance the inference of deep inverse networks by ensuring consistency with the forward model. Specifically, given an initial estimate from a learned reconstruction network, we apply a projection step that constrains the solution to lie within the valid solution space of the inverse problem. We theoretically demonstrate that if"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15777","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/2505.15777/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":"2505.15777","created_at":"2026-07-05T11:06:57.789635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15777v1","created_at":"2026-07-05T11:06:57.789635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15777","created_at":"2026-07-05T11:06:57.789635+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCOFV2WPWLTX","created_at":"2026-07-05T11:06:57.789635+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCOFV2WPWLTXMCVF","created_at":"2026-07-05T11:06:57.789635+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCOFV2WP","created_at":"2026-07-05T11:06:57.789635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15777","citing_title":"Projection-Based Correction for Enhancing Deep Inverse Networks","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25","json":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25.json","graph_json":"https://pith.science/api/pith-number/GCOFV2WPWLTXMCVFDOQBDWYX25/graph.json","events_json":"https://pith.science/api/pith-number/GCOFV2WPWLTXMCVFDOQBDWYX25/events.json","paper":"https://pith.science/paper/GCOFV2WP"},"agent_actions":{"view_html":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25","download_json":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25.json","view_paper":"https://pith.science/paper/GCOFV2WP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15777&json=true","fetch_graph":"https://pith.science/api/pith-number/GCOFV2WPWLTXMCVFDOQBDWYX25/graph.json","fetch_events":"https://pith.science/api/pith-number/GCOFV2WPWLTXMCVFDOQBDWYX25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25/action/storage_attestation","attest_author":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25/action/author_attestation","sign_citation":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25/action/citation_signature","submit_replication":"https://pith.science/pith/GCOFV2WPWLTXMCVFDOQBDWYX25/action/replication_record"}},"created_at":"2026-07-05T11:06:57.789635+00:00","updated_at":"2026-07-05T11:06:57.789635+00:00"}