{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7XLBIVLF7TJDSPD7BNG5BOAN3O","short_pith_number":"pith:7XLBIVLF","schema_version":"1.0","canonical_sha256":"fdd6145565fcd2393c7f0b4dd0b80ddbad1ed952a5f8e18cfcf497b083dd156b","source":{"kind":"arxiv","id":"2002.05692","version":1},"attestation_state":"computed","paper":{"title":"Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","q-bio.QM"],"primary_cat":"eess.IV","authors_text":"Carole H. Sudre, Mark Graham, M. Jorge Cardoso, Parashkev Nachev, Petru-Daniel Tudosiu, Richard Shaw, Sebastien Ourselin, Thomas Varsavsky","submitted_at":"2020-02-13T18:18:51Z","abstract_excerpt":"The increasing efficiency and compactness of deep learning architectures, together with hardware improvements, have enabled the complex and high-dimensional modelling of medical volumetric data at higher resolutions. Recently, Vector-Quantised Variational Autoencoders (VQ-VAE) have been proposed as an efficient generative unsupervised learning approach that can encode images to a small percentage of their initial size, while preserving their decoded fidelity. Here, we show a VQ-VAE inspired network can efficiently encode a full-resolution 3D brain volume, compressing the data to $0.825\\%$ of t"},"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":"2002.05692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-02-13T18:18:51Z","cross_cats_sorted":["cs.CV","q-bio.QM"],"title_canon_sha256":"b35215fe1fc88b76d2ba4cf86474edc01803444a3c1c9ba54482897912a1768f","abstract_canon_sha256":"7299569a2908b79722ca38bc93702cf93a62d4924a57d10d3ac0a010282d88ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:33.549264Z","signature_b64":"F1/L2trAZ0pAYAfYpKum5ZX/WggbEQ7JEKr8lVEJ5kSbZBcmEtes+Q/XmklcYasGfhDyY3uqn8wNQ2a9GInxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdd6145565fcd2393c7f0b4dd0b80ddbad1ed952a5f8e18cfcf497b083dd156b","last_reissued_at":"2026-07-05T00:40:33.548722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:33.548722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","q-bio.QM"],"primary_cat":"eess.IV","authors_text":"Carole H. Sudre, Mark Graham, M. Jorge Cardoso, Parashkev Nachev, Petru-Daniel Tudosiu, Richard Shaw, Sebastien Ourselin, Thomas Varsavsky","submitted_at":"2020-02-13T18:18:51Z","abstract_excerpt":"The increasing efficiency and compactness of deep learning architectures, together with hardware improvements, have enabled the complex and high-dimensional modelling of medical volumetric data at higher resolutions. Recently, Vector-Quantised Variational Autoencoders (VQ-VAE) have been proposed as an efficient generative unsupervised learning approach that can encode images to a small percentage of their initial size, while preserving their decoded fidelity. Here, we show a VQ-VAE inspired network can efficiently encode a full-resolution 3D brain volume, compressing the data to $0.825\\%$ of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05692","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/2002.05692/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":"2002.05692","created_at":"2026-07-05T00:40:33.548787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05692v1","created_at":"2026-07-05T00:40:33.548787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05692","created_at":"2026-07-05T00:40:33.548787+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XLBIVLF7TJD","created_at":"2026-07-05T00:40:33.548787+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XLBIVLF7TJDSPD7","created_at":"2026-07-05T00:40:33.548787+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XLBIVLF","created_at":"2026-07-05T00:40:33.548787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05713","citing_title":"4D VQ-GAN: Synthesising Medical Scans at Any Time Point for Personalised Disease Progression Modelling of Idiopathic Pulmonary Fibrosis","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O","json":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O.json","graph_json":"https://pith.science/api/pith-number/7XLBIVLF7TJDSPD7BNG5BOAN3O/graph.json","events_json":"https://pith.science/api/pith-number/7XLBIVLF7TJDSPD7BNG5BOAN3O/events.json","paper":"https://pith.science/paper/7XLBIVLF"},"agent_actions":{"view_html":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O","download_json":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O.json","view_paper":"https://pith.science/paper/7XLBIVLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05692&json=true","fetch_graph":"https://pith.science/api/pith-number/7XLBIVLF7TJDSPD7BNG5BOAN3O/graph.json","fetch_events":"https://pith.science/api/pith-number/7XLBIVLF7TJDSPD7BNG5BOAN3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O/action/storage_attestation","attest_author":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O/action/author_attestation","sign_citation":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O/action/citation_signature","submit_replication":"https://pith.science/pith/7XLBIVLF7TJDSPD7BNG5BOAN3O/action/replication_record"}},"created_at":"2026-07-05T00:40:33.548787+00:00","updated_at":"2026-07-05T00:40:33.548787+00:00"}