{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XYLMFPO5R2L5Y5BEFZAYBI6T35","short_pith_number":"pith:XYLMFPO5","schema_version":"1.0","canonical_sha256":"be16c2bddd8e97dc74242e4180a3d3df79259a2ae354720f2515ed5d3960b83e","source":{"kind":"arxiv","id":"2311.02762","version":2},"attestation_state":"computed","paper":{"title":"Fast Sparse 3D Convolution Network with VDB","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anyong Mao, Eftychios Sifakis, Fangjun Zhou","submitted_at":"2023-11-05T20:43:46Z","abstract_excerpt":"We proposed a new Convolution Neural Network implementation optimized for sparse 3D data inference. This implementation uses NanoVDB as the data structure to store the sparse tensor. It leaves a relatively small memory footprint while maintaining high performance. We demonstrate that this architecture is around 20 times faster than the state-of-the-art dense CNN model on a high-resolution 3D object classification network."},"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":"2311.02762","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-05T20:43:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d3cd69c797b5430b3016eaa09b6a5bb3c66761407425ed2e9b7626b7f4ddfe0","abstract_canon_sha256":"5a8d6903b51a663de07ca7235b366afff37776327230e88b9e3f2fd1a58ee050"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:55.299960Z","signature_b64":"NfwFefJcK5IhJ2pJ0bOB94GtiCwLnOpUDkirZqp46Cqh+Uc1Ghnz4xWDy5gVHRCD9Ro/CQj4gNRcJ5EbIQwrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be16c2bddd8e97dc74242e4180a3d3df79259a2ae354720f2515ed5d3960b83e","last_reissued_at":"2026-07-05T07:12:55.299413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:55.299413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Sparse 3D Convolution Network with VDB","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anyong Mao, Eftychios Sifakis, Fangjun Zhou","submitted_at":"2023-11-05T20:43:46Z","abstract_excerpt":"We proposed a new Convolution Neural Network implementation optimized for sparse 3D data inference. This implementation uses NanoVDB as the data structure to store the sparse tensor. It leaves a relatively small memory footprint while maintaining high performance. We demonstrate that this architecture is around 20 times faster than the state-of-the-art dense CNN model on a high-resolution 3D object classification network."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02762","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/2311.02762/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":"2311.02762","created_at":"2026-07-05T07:12:55.299472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02762v2","created_at":"2026-07-05T07:12:55.299472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02762","created_at":"2026-07-05T07:12:55.299472+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYLMFPO5R2L5","created_at":"2026-07-05T07:12:55.299472+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYLMFPO5R2L5Y5BE","created_at":"2026-07-05T07:12:55.299472+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYLMFPO5","created_at":"2026-07-05T07:12:55.299472+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/XYLMFPO5R2L5Y5BEFZAYBI6T35","json":"https://pith.science/pith/XYLMFPO5R2L5Y5BEFZAYBI6T35.json","graph_json":"https://pith.science/api/pith-number/XYLMFPO5R2L5Y5BEFZAYBI6T35/graph.json","events_json":"https://pith.science/api/pith-number/XYLMFPO5R2L5Y5BEFZAYBI6T35/events.json","paper":"https://pith.science/paper/XYLMFPO5"},"agent_actions":{"view_html":"https://pith.science/pith/XYLMFPO5R2L5Y5BEFZAYBI6T35","download_json":"https://pith.science/pith/XYLMFPO5R2L5Y5BEFZAYBI6T35.json","view_paper":"https://pith.science/paper/XYLMFPO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02762&json=true","fetch_graph":"https://pith.science/api/pith-number/XYLMFPO5R2L5Y5BEFZAYBI6T35/graph.json","fetch_events":"https://pith.science/api/pith-number/XYLMFPO5R2L5Y5BEFZAYBI6T35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYLMFPO5R2L5Y5BEFZAYBI6T35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYLMFPO5R2L5Y5BEFZAYBI6T35/action/storage_attestation","attest_author":"https://pith.science/pith/XYLMFPO5R2L5Y5BEFZAYBI6T35/action/author_attestation","sign_citation":"https://pith.science/pith/XYLMFPO5R2L5Y5BEFZAYBI6T35/action/citation_signature","submit_replication":"https://pith.science/pith/XYLMFPO5R2L5Y5BEFZAYBI6T35/action/replication_record"}},"created_at":"2026-07-05T07:12:55.299472+00:00","updated_at":"2026-07-05T07:12:55.299472+00:00"}