{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3KSBCA2X4K7MX3NEF6I4BXOW3Q","short_pith_number":"pith:3KSBCA2X","schema_version":"1.0","canonical_sha256":"daa4110357e2becbeda42f91c0ddd6dc0caed770f39985680b21d2156c2f3b78","source":{"kind":"arxiv","id":"2304.05448","version":2},"attestation_state":"computed","paper":{"title":"Scale-Space Hypernetworks for Efficient Biomedical Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrian Dalca, John Guttag, Jose Javier Gonzalez Ortiz","submitted_at":"2023-04-11T18:38:57Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are the predominant model used for a variety of medical image analysis tasks. At inference time, these models are computationally intensive, especially with volumetric data. In principle, it is possible to trade accuracy for computational efficiency by manipulating the rescaling factor in the downsample and upsample layers of CNN architectures. However, properly exploring the accuracy-efficiency trade-off is prohibitively expensive with existing models. To address this, we introduce Scale-Space HyperNetworks (SSHN), a method that learns a spectrum of CNNs w"},"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":"2304.05448","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-11T18:38:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"82d0bb97baa9391c1e344f15b52f15832c0aec738e596fff4d8ce91935fbdf8a","abstract_canon_sha256":"2176a9315334bfc982b3279de1dd2a983875dca0541becae30299e5896bb51c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:01.482007Z","signature_b64":"a04eziK1iDF72Nbix7BO72ig2VQZvGqRvwYZ7V8FnmDQkr4bKaByzVS7GxgKX53GhjB7tpN5dktsg2vjKK53CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daa4110357e2becbeda42f91c0ddd6dc0caed770f39985680b21d2156c2f3b78","last_reissued_at":"2026-07-05T06:26:01.481576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:01.481576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale-Space Hypernetworks for Efficient Biomedical Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrian Dalca, John Guttag, Jose Javier Gonzalez Ortiz","submitted_at":"2023-04-11T18:38:57Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are the predominant model used for a variety of medical image analysis tasks. At inference time, these models are computationally intensive, especially with volumetric data. In principle, it is possible to trade accuracy for computational efficiency by manipulating the rescaling factor in the downsample and upsample layers of CNN architectures. However, properly exploring the accuracy-efficiency trade-off is prohibitively expensive with existing models. To address this, we introduce Scale-Space HyperNetworks (SSHN), a method that learns a spectrum of CNNs w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05448","kind":"arxiv","version":2},"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/2304.05448/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":"2304.05448","created_at":"2026-07-05T06:26:01.481630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.05448v2","created_at":"2026-07-05T06:26:01.481630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05448","created_at":"2026-07-05T06:26:01.481630+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KSBCA2X4K7M","created_at":"2026-07-05T06:26:01.481630+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KSBCA2X4K7MX3NE","created_at":"2026-07-05T06:26:01.481630+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KSBCA2X","created_at":"2026-07-05T06:26:01.481630+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/3KSBCA2X4K7MX3NEF6I4BXOW3Q","json":"https://pith.science/pith/3KSBCA2X4K7MX3NEF6I4BXOW3Q.json","graph_json":"https://pith.science/api/pith-number/3KSBCA2X4K7MX3NEF6I4BXOW3Q/graph.json","events_json":"https://pith.science/api/pith-number/3KSBCA2X4K7MX3NEF6I4BXOW3Q/events.json","paper":"https://pith.science/paper/3KSBCA2X"},"agent_actions":{"view_html":"https://pith.science/pith/3KSBCA2X4K7MX3NEF6I4BXOW3Q","download_json":"https://pith.science/pith/3KSBCA2X4K7MX3NEF6I4BXOW3Q.json","view_paper":"https://pith.science/paper/3KSBCA2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.05448&json=true","fetch_graph":"https://pith.science/api/pith-number/3KSBCA2X4K7MX3NEF6I4BXOW3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/3KSBCA2X4K7MX3NEF6I4BXOW3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KSBCA2X4K7MX3NEF6I4BXOW3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KSBCA2X4K7MX3NEF6I4BXOW3Q/action/storage_attestation","attest_author":"https://pith.science/pith/3KSBCA2X4K7MX3NEF6I4BXOW3Q/action/author_attestation","sign_citation":"https://pith.science/pith/3KSBCA2X4K7MX3NEF6I4BXOW3Q/action/citation_signature","submit_replication":"https://pith.science/pith/3KSBCA2X4K7MX3NEF6I4BXOW3Q/action/replication_record"}},"created_at":"2026-07-05T06:26:01.481630+00:00","updated_at":"2026-07-05T06:26:01.481630+00:00"}