{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6SDYDU2MIBAT32HUEV6SYXEAAJ","short_pith_number":"pith:6SDYDU2M","schema_version":"1.0","canonical_sha256":"f48781d34c40413de8f4257d2c5c8002556fd63623dd25e1fd3002c92ba8565c","source":{"kind":"arxiv","id":"2204.10319","version":1},"attestation_state":"computed","paper":{"title":"TorchSparse: Efficient Point Cloud Inference Engine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.PF"],"primary_cat":"cs.LG","authors_text":"Haotian Tang, Song Han, Xiuyu Li, Yujun Lin, Zhijian Liu","submitted_at":"2022-04-21T17:58:30Z","abstract_excerpt":"Deep learning on point clouds has received increased attention thanks to its wide applications in AR/VR and autonomous driving. These applications require low latency and high accuracy to provide real-time user experience and ensure user safety. Unlike conventional dense workloads, the sparse and irregular nature of point clouds poses severe challenges to running sparse CNNs efficiently on the general-purpose hardware. Furthermore, existing sparse acceleration techniques for 2D images do not translate to 3D point clouds. In this paper, we introduce TorchSparse, a high-performance point cloud i"},"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":"2204.10319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T17:58:30Z","cross_cats_sorted":["cs.CV","cs.PF"],"title_canon_sha256":"11acd34a8c8265f7357d2d861769be29ba7e5d7408ba46f8de0a00383e0076bf","abstract_canon_sha256":"e07a1e1bbdc859912eb54d986a3960d4767680e9a212bcded4d49250131dc136"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:49.022776Z","signature_b64":"eQaTTOuEThHLs81gU1buyydZUeaZMGD/LskhbBxWCXlEzzEEbkH5JwlCcpIt3eZWOokRPWiefKbnFWNbnA27AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f48781d34c40413de8f4257d2c5c8002556fd63623dd25e1fd3002c92ba8565c","last_reissued_at":"2026-07-05T04:16:49.022249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:49.022249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TorchSparse: Efficient Point Cloud Inference Engine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.PF"],"primary_cat":"cs.LG","authors_text":"Haotian Tang, Song Han, Xiuyu Li, Yujun Lin, Zhijian Liu","submitted_at":"2022-04-21T17:58:30Z","abstract_excerpt":"Deep learning on point clouds has received increased attention thanks to its wide applications in AR/VR and autonomous driving. These applications require low latency and high accuracy to provide real-time user experience and ensure user safety. Unlike conventional dense workloads, the sparse and irregular nature of point clouds poses severe challenges to running sparse CNNs efficiently on the general-purpose hardware. Furthermore, existing sparse acceleration techniques for 2D images do not translate to 3D point clouds. In this paper, we introduce TorchSparse, a high-performance point cloud i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10319","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/2204.10319/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":"2204.10319","created_at":"2026-07-05T04:16:49.022325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.10319v1","created_at":"2026-07-05T04:16:49.022325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10319","created_at":"2026-07-05T04:16:49.022325+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SDYDU2MIBAT","created_at":"2026-07-05T04:16:49.022325+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SDYDU2MIBAT32HU","created_at":"2026-07-05T04:16:49.022325+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SDYDU2M","created_at":"2026-07-05T04:16:49.022325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11698","citing_title":"Fusion of multi-source precipitation records via coordinate-based generative model","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ","json":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ.json","graph_json":"https://pith.science/api/pith-number/6SDYDU2MIBAT32HUEV6SYXEAAJ/graph.json","events_json":"https://pith.science/api/pith-number/6SDYDU2MIBAT32HUEV6SYXEAAJ/events.json","paper":"https://pith.science/paper/6SDYDU2M"},"agent_actions":{"view_html":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ","download_json":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ.json","view_paper":"https://pith.science/paper/6SDYDU2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.10319&json=true","fetch_graph":"https://pith.science/api/pith-number/6SDYDU2MIBAT32HUEV6SYXEAAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6SDYDU2MIBAT32HUEV6SYXEAAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ/action/storage_attestation","attest_author":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ/action/author_attestation","sign_citation":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ/action/citation_signature","submit_replication":"https://pith.science/pith/6SDYDU2MIBAT32HUEV6SYXEAAJ/action/replication_record"}},"created_at":"2026-07-05T04:16:49.022325+00:00","updated_at":"2026-07-05T04:16:49.022325+00:00"}