{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AIOWUMYJDWKNWJ6MPXN5ZWM2X3","short_pith_number":"pith:AIOWUMYJ","schema_version":"1.0","canonical_sha256":"021d6a33091d94db27cc7ddbdcd99abecf455dcd20beea7d464dae1b40f9585b","source":{"kind":"arxiv","id":"2401.00912","version":2},"attestation_state":"computed","paper":{"title":"ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhang He, Guowen Zhang, Lei Zhang, Ruihuang Li","submitted_at":"2024-01-01T02:29:59Z","abstract_excerpt":"Window-based transformers excel in large-scale point cloud understanding by capturing context-aware representations with affordable attention computation in a more localized manner. However, the sparse nature of point clouds leads to a significant variance in the number of voxels per window. Existing methods group the voxels in each window into fixed-length sequences through extensive sorting and padding operations, resulting in a non-negligible computational and memory overhead. In this paper, we introduce ScatterFormer, which to the best of our knowledge, is the first to directly apply atten"},"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":"2401.00912","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-01T02:29:59Z","cross_cats_sorted":[],"title_canon_sha256":"9c1a6d74dac9c6894170e2d716b2d994560638b757cc20005481a05810d50bec","abstract_canon_sha256":"c9f2fbea967426d69c2c66a0891083f9b8e2397335619de21f898827ca4f1f01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:24.414209Z","signature_b64":"rLi5x9TkxDRc4tT8k32rZtZzu19IxzqhYu9VD9Wyfz/GmnjyNK5bGH+hpZWrCH4ODj58JcgSGDb72RvbRKloCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"021d6a33091d94db27cc7ddbdcd99abecf455dcd20beea7d464dae1b40f9585b","last_reissued_at":"2026-07-05T08:45:24.413801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:24.413801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhang He, Guowen Zhang, Lei Zhang, Ruihuang Li","submitted_at":"2024-01-01T02:29:59Z","abstract_excerpt":"Window-based transformers excel in large-scale point cloud understanding by capturing context-aware representations with affordable attention computation in a more localized manner. However, the sparse nature of point clouds leads to a significant variance in the number of voxels per window. Existing methods group the voxels in each window into fixed-length sequences through extensive sorting and padding operations, resulting in a non-negligible computational and memory overhead. In this paper, we introduce ScatterFormer, which to the best of our knowledge, is the first to directly apply atten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00912","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/2401.00912/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":"2401.00912","created_at":"2026-07-05T08:45:24.413853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00912v2","created_at":"2026-07-05T08:45:24.413853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00912","created_at":"2026-07-05T08:45:24.413853+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIOWUMYJDWKN","created_at":"2026-07-05T08:45:24.413853+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIOWUMYJDWKNWJ6M","created_at":"2026-07-05T08:45:24.413853+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIOWUMYJ","created_at":"2026-07-05T08:45:24.413853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11540","citing_title":"SP$^2$T: Sparse Proxy Attention for Dual-stream Point Transformer","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3","json":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3.json","graph_json":"https://pith.science/api/pith-number/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/graph.json","events_json":"https://pith.science/api/pith-number/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/events.json","paper":"https://pith.science/paper/AIOWUMYJ"},"agent_actions":{"view_html":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3","download_json":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3.json","view_paper":"https://pith.science/paper/AIOWUMYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00912&json=true","fetch_graph":"https://pith.science/api/pith-number/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/graph.json","fetch_events":"https://pith.science/api/pith-number/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/action/storage_attestation","attest_author":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/action/author_attestation","sign_citation":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/action/citation_signature","submit_replication":"https://pith.science/pith/AIOWUMYJDWKNWJ6MPXN5ZWM2X3/action/replication_record"}},"created_at":"2026-07-05T08:45:24.413853+00:00","updated_at":"2026-07-05T08:45:24.413853+00:00"}