{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FDWMVI2JGENNJCXVQWN2FB5THQ","short_pith_number":"pith:FDWMVI2J","schema_version":"1.0","canonical_sha256":"28eccaa349311ad48af5859ba287b33c24cc945369beca82f2cee3677b8d8126","source":{"kind":"arxiv","id":"1706.01307","version":1},"attestation_state":"computed","paper":{"title":"Submanifold Sparse Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Benjamin Graham, Laurens van der Maaten","submitted_at":"2017-06-05T13:25:24Z","abstract_excerpt":"Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc. Whilst some of this data is naturally dense (for instance, photos), many other data sources are inherently sparse. Examples include pen-strokes forming on a piece of paper, or (colored) 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard \"dense\" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce a sparse convolutional operation tailored to processing sparse data that differs from prio"},"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":"1706.01307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-06-05T13:25:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"267e9c6e62a24cd483a0c3d116ff3af44ce8b7d5b5720bfd73f15a39c061ee65","abstract_canon_sha256":"78bb6336435ad5b9f1663b93a3f7d6ae9c0715a6b2485670683642c2ef8cd3f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:03.929160Z","signature_b64":"E2hpGqxs9Mnopaa3L/QgJBXOx/pEv7W+lUVWUINmm1GRCXCpHBrFzQi/O2OJvfTPqGRgyd33zzC/GgCs0hLnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28eccaa349311ad48af5859ba287b33c24cc945369beca82f2cee3677b8d8126","last_reissued_at":"2026-05-18T00:43:03.928650Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:03.928650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Submanifold Sparse Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Benjamin Graham, Laurens van der Maaten","submitted_at":"2017-06-05T13:25:24Z","abstract_excerpt":"Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc. Whilst some of this data is naturally dense (for instance, photos), many other data sources are inherently sparse. Examples include pen-strokes forming on a piece of paper, or (colored) 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard \"dense\" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce a sparse convolutional operation tailored to processing sparse data that differs from prio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01307","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":""},"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":"1706.01307","created_at":"2026-05-18T00:43:03.928720+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01307v1","created_at":"2026-05-18T00:43:03.928720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01307","created_at":"2026-05-18T00:43:03.928720+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDWMVI2JGENN","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDWMVI2JGENNJCXV","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDWMVI2J","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1907.05091","citing_title":"Efficient Semantic Scene Completion Network with Spatial Group Convolution","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2505.17674","citing_title":"SVL: Spike-based Vision-language Pretraining for Efficient 3D Open-world Understanding","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2512.14692","citing_title":"Native and Compact Structured Latents for 3D Generation","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2511.04334","citing_title":"Submanifold Sparse Convolutional Networks for Automated 3D Segmentation of Kidneys and Kidney Tumours in Computed Tomography","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11111","citing_title":"ShardTensor: Domain Parallelism for Scientific Machine Learning","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ","json":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ.json","graph_json":"https://pith.science/api/pith-number/FDWMVI2JGENNJCXVQWN2FB5THQ/graph.json","events_json":"https://pith.science/api/pith-number/FDWMVI2JGENNJCXVQWN2FB5THQ/events.json","paper":"https://pith.science/paper/FDWMVI2J"},"agent_actions":{"view_html":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ","download_json":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ.json","view_paper":"https://pith.science/paper/FDWMVI2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01307&json=true","fetch_graph":"https://pith.science/api/pith-number/FDWMVI2JGENNJCXVQWN2FB5THQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FDWMVI2JGENNJCXVQWN2FB5THQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ/action/storage_attestation","attest_author":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ/action/author_attestation","sign_citation":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ/action/citation_signature","submit_replication":"https://pith.science/pith/FDWMVI2JGENNJCXVQWN2FB5THQ/action/replication_record"}},"created_at":"2026-05-18T00:43:03.928720+00:00","updated_at":"2026-05-18T00:43:03.928720+00:00"}