{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3K36DMOK4QPH2AVHCNDBASGSFP","short_pith_number":"pith:3K36DMOK","schema_version":"1.0","canonical_sha256":"dab7e1b1cae41e7d02a713461048d22bded623b9abd6f2e70d3e31a85d861163","source":{"kind":"arxiv","id":"2108.06076","version":4},"attestation_state":"computed","paper":{"title":"PVT: Point-Voxel Transformer for Point Cloud Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Cheng Zhang, Haocheng Wan, Xinyi Shen, Zizhao Wu","submitted_at":"2021-08-13T06:07:57Z","abstract_excerpt":"The recently developed pure Transformer architectures have attained promising accuracy on point cloud learning benchmarks compared to convolutional neural networks. However, existing point cloud Transformers are computationally expensive since they waste a significant amount of time on structuring the irregular data. To solve this shortcoming, we present Sparse Window Attention (SWA) module to gather coarse-grained local features from non-empty voxels, which not only bypasses the expensive irregular data structuring and invalid empty voxel computation, but also obtains linear computational com"},"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":"2108.06076","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-13T06:07:57Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"b3e197db6dbf7451ba446aa341667da3861b70ac99d3deabedbfb50611c53eda","abstract_canon_sha256":"2c639f2b4e53017846063b0a4927d8b249bb084365d01cf307a90b6ffabf6f42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:19.967894Z","signature_b64":"mWUklt96Rp/PntgHh9AIXcO9qbNCXa6fCOOHGigMh9sGOcWiCdcUiwDBdexoQ8eKUSeXHoQ1nt2Zpnv1uC+dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dab7e1b1cae41e7d02a713461048d22bded623b9abd6f2e70d3e31a85d861163","last_reissued_at":"2026-07-05T04:26:19.967405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:19.967405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PVT: Point-Voxel Transformer for Point Cloud Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Cheng Zhang, Haocheng Wan, Xinyi Shen, Zizhao Wu","submitted_at":"2021-08-13T06:07:57Z","abstract_excerpt":"The recently developed pure Transformer architectures have attained promising accuracy on point cloud learning benchmarks compared to convolutional neural networks. However, existing point cloud Transformers are computationally expensive since they waste a significant amount of time on structuring the irregular data. To solve this shortcoming, we present Sparse Window Attention (SWA) module to gather coarse-grained local features from non-empty voxels, which not only bypasses the expensive irregular data structuring and invalid empty voxel computation, but also obtains linear computational com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.06076","kind":"arxiv","version":4},"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/2108.06076/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":"2108.06076","created_at":"2026-07-05T04:26:19.967460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.06076v4","created_at":"2026-07-05T04:26:19.967460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.06076","created_at":"2026-07-05T04:26:19.967460+00:00"},{"alias_kind":"pith_short_12","alias_value":"3K36DMOK4QPH","created_at":"2026-07-05T04:26:19.967460+00:00"},{"alias_kind":"pith_short_16","alias_value":"3K36DMOK4QPH2AVH","created_at":"2026-07-05T04:26:19.967460+00:00"},{"alias_kind":"pith_short_8","alias_value":"3K36DMOK","created_at":"2026-07-05T04:26:19.967460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10780","citing_title":"LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learning","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP","json":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP.json","graph_json":"https://pith.science/api/pith-number/3K36DMOK4QPH2AVHCNDBASGSFP/graph.json","events_json":"https://pith.science/api/pith-number/3K36DMOK4QPH2AVHCNDBASGSFP/events.json","paper":"https://pith.science/paper/3K36DMOK"},"agent_actions":{"view_html":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP","download_json":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP.json","view_paper":"https://pith.science/paper/3K36DMOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.06076&json=true","fetch_graph":"https://pith.science/api/pith-number/3K36DMOK4QPH2AVHCNDBASGSFP/graph.json","fetch_events":"https://pith.science/api/pith-number/3K36DMOK4QPH2AVHCNDBASGSFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP/action/storage_attestation","attest_author":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP/action/author_attestation","sign_citation":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP/action/citation_signature","submit_replication":"https://pith.science/pith/3K36DMOK4QPH2AVHCNDBASGSFP/action/replication_record"}},"created_at":"2026-07-05T04:26:19.967460+00:00","updated_at":"2026-07-05T04:26:19.967460+00:00"}