{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DLAX5SLCRUSLXQ62UGXBYXVGEW","short_pith_number":"pith:DLAX5SLC","schema_version":"1.0","canonical_sha256":"1ac17ec9628d24bbc3daa1ae1c5ea625bcd2e7b2f72322fa6996b01348295ae4","source":{"kind":"arxiv","id":"2208.04448","version":2},"attestation_state":"computed","paper":{"title":"NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR"],"primary_cat":"cs.LG","authors_text":"Doyub Kim, Ken Museth, Minjae Lee","submitted_at":"2022-08-08T22:21:22Z","abstract_excerpt":"We introduce NeuralVDB, which improves on an existing industry standard for efficient storage of sparse volumetric data, denoted VDB [Museth 2013], by leveraging recent advancements in machine learning. Our novel hybrid data structure can reduce the memory footprints of VDB volumes by orders of magnitude, while maintaining its flexibility and only incurring small (user-controlled) compression errors. Specifically, NeuralVDB replaces the lower nodes of a shallow and wide VDB tree structure with multiple hierarchical neural networks that separately encode topology and value information by means "},"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":"2208.04448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-08T22:21:22Z","cross_cats_sorted":["cs.CV","cs.GR"],"title_canon_sha256":"2e6efa9230f0cac384b6b9bea2ae5bc9b9ed4c2cfd3f3b8292852a453c8c39df","abstract_canon_sha256":"78f2551cd0ca27ecadb9a5beeefb56c7b8098d071376a4740d782ffad96382e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:50.609571Z","signature_b64":"QPVtK7hQ2Bj2nschMBW3XfP6xqSBXrwRDtifFQNbRVlgGIfyPfQsSNCEUW8+eVPOr7kTBmEdSFnJO19bGcGRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ac17ec9628d24bbc3daa1ae1c5ea625bcd2e7b2f72322fa6996b01348295ae4","last_reissued_at":"2026-07-05T07:43:50.608899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:50.608899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR"],"primary_cat":"cs.LG","authors_text":"Doyub Kim, Ken Museth, Minjae Lee","submitted_at":"2022-08-08T22:21:22Z","abstract_excerpt":"We introduce NeuralVDB, which improves on an existing industry standard for efficient storage of sparse volumetric data, denoted VDB [Museth 2013], by leveraging recent advancements in machine learning. Our novel hybrid data structure can reduce the memory footprints of VDB volumes by orders of magnitude, while maintaining its flexibility and only incurring small (user-controlled) compression errors. Specifically, NeuralVDB replaces the lower nodes of a shallow and wide VDB tree structure with multiple hierarchical neural networks that separately encode topology and value information by means "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04448","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/2208.04448/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":"2208.04448","created_at":"2026-07-05T07:43:50.609008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.04448v2","created_at":"2026-07-05T07:43:50.609008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04448","created_at":"2026-07-05T07:43:50.609008+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLAX5SLCRUSL","created_at":"2026-07-05T07:43:50.609008+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLAX5SLCRUSLXQ62","created_at":"2026-07-05T07:43:50.609008+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLAX5SLC","created_at":"2026-07-05T07:43:50.609008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15722","citing_title":"INRet: A General Framework for Accurate Retrieval of INRs for Shapes","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW","json":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW.json","graph_json":"https://pith.science/api/pith-number/DLAX5SLCRUSLXQ62UGXBYXVGEW/graph.json","events_json":"https://pith.science/api/pith-number/DLAX5SLCRUSLXQ62UGXBYXVGEW/events.json","paper":"https://pith.science/paper/DLAX5SLC"},"agent_actions":{"view_html":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW","download_json":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW.json","view_paper":"https://pith.science/paper/DLAX5SLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.04448&json=true","fetch_graph":"https://pith.science/api/pith-number/DLAX5SLCRUSLXQ62UGXBYXVGEW/graph.json","fetch_events":"https://pith.science/api/pith-number/DLAX5SLCRUSLXQ62UGXBYXVGEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW/action/storage_attestation","attest_author":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW/action/author_attestation","sign_citation":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW/action/citation_signature","submit_replication":"https://pith.science/pith/DLAX5SLCRUSLXQ62UGXBYXVGEW/action/replication_record"}},"created_at":"2026-07-05T07:43:50.609008+00:00","updated_at":"2026-07-05T07:43:50.609008+00:00"}