{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YLHSMG2CJEIEXIHLWRLSSBRJZR","short_pith_number":"pith:YLHSMG2C","schema_version":"1.0","canonical_sha256":"c2cf261b4249104ba0ebb457290629cc7b2c6cbe8d4cab0da628409bf87d0d54","source":{"kind":"arxiv","id":"2501.17898","version":1},"attestation_state":"computed","paper":{"title":"Distilling Knowledge for Designing Computational Imaging Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Henry Arguello, Leon Suarez-Rodriguez, Roman Jacome","submitted_at":"2025-01-29T03:49:21Z","abstract_excerpt":"Designing the physical encoder is crucial for accurate image reconstruction in computational imaging (CI) systems. Currently, these systems are designed via end-to-end (E2E) optimization, where the encoder is modeled as a neural network layer and is jointly optimized with the decoder. However, the performance of E2E optimization is significantly reduced by the physical constraints imposed on the encoder. Also, since the E2E learns the parameters of the encoder by backpropagating the reconstruction error, it does not promote optimal intermediate outputs and suffers from gradient vanishing. To a"},"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":"2501.17898","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-01-29T03:49:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62f29b22633b6fef42c8ddb4d99917ca4d935478cdfe1b28b4d958245d8fa13f","abstract_canon_sha256":"9fbcd78215c8a8d3cd046740bc3fdfba9fcfb206a17261403705ed1b4e5cf147"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:04.033340Z","signature_b64":"aos3zyly944RG6ribUsJMO3fkNur3iBgHd+MXTs1dsAgbitohQygjIltYBWhbfVkvFFTteaI7y9IW9m3mB0aBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2cf261b4249104ba0ebb457290629cc7b2c6cbe8d4cab0da628409bf87d0d54","last_reissued_at":"2026-07-05T10:07:04.032903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:04.032903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Knowledge for Designing Computational Imaging Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Henry Arguello, Leon Suarez-Rodriguez, Roman Jacome","submitted_at":"2025-01-29T03:49:21Z","abstract_excerpt":"Designing the physical encoder is crucial for accurate image reconstruction in computational imaging (CI) systems. Currently, these systems are designed via end-to-end (E2E) optimization, where the encoder is modeled as a neural network layer and is jointly optimized with the decoder. However, the performance of E2E optimization is significantly reduced by the physical constraints imposed on the encoder. Also, since the E2E learns the parameters of the encoder by backpropagating the reconstruction error, it does not promote optimal intermediate outputs and suffers from gradient vanishing. To a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17898","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/2501.17898/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":"2501.17898","created_at":"2026-07-05T10:07:04.032962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17898v1","created_at":"2026-07-05T10:07:04.032962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17898","created_at":"2026-07-05T10:07:04.032962+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLHSMG2CJEIE","created_at":"2026-07-05T10:07:04.032962+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLHSMG2CJEIEXIHL","created_at":"2026-07-05T10:07:04.032962+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLHSMG2C","created_at":"2026-07-05T10:07:04.032962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.04832","citing_title":"Deep Distillation Gradient Preconditioning for Inverse Problems","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR","json":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR.json","graph_json":"https://pith.science/api/pith-number/YLHSMG2CJEIEXIHLWRLSSBRJZR/graph.json","events_json":"https://pith.science/api/pith-number/YLHSMG2CJEIEXIHLWRLSSBRJZR/events.json","paper":"https://pith.science/paper/YLHSMG2C"},"agent_actions":{"view_html":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR","download_json":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR.json","view_paper":"https://pith.science/paper/YLHSMG2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17898&json=true","fetch_graph":"https://pith.science/api/pith-number/YLHSMG2CJEIEXIHLWRLSSBRJZR/graph.json","fetch_events":"https://pith.science/api/pith-number/YLHSMG2CJEIEXIHLWRLSSBRJZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR/action/storage_attestation","attest_author":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR/action/author_attestation","sign_citation":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR/action/citation_signature","submit_replication":"https://pith.science/pith/YLHSMG2CJEIEXIHLWRLSSBRJZR/action/replication_record"}},"created_at":"2026-07-05T10:07:04.032962+00:00","updated_at":"2026-07-05T10:07:04.032962+00:00"}