{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ECYAZ7RM7KJSWO3R34YD3RYO3U","short_pith_number":"pith:ECYAZ7RM","schema_version":"1.0","canonical_sha256":"20b00cfe2cfa932b3b71df303dc70edd1f1781700ed6e6b08bbaeb966fedf65f","source":{"kind":"arxiv","id":"2103.14635","version":2},"attestation_state":"computed","paper":{"title":"PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Mutian Xu, Runyu Ding, Xiaojuan Qi","submitted_at":"2021-03-26T17:52:38Z","abstract_excerpt":"We introduce Position Adaptive Convolution (PAConv), a generic convolution operation for 3D point cloud processing. The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet. In this way, the kernel is built in a data-driven manner, endowing PAConv with more flexibility than 2D convolutions to better handle the irregular and unordered point cloud data. Besides, the complexity of the learning process is reduced by"},"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":"2103.14635","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-26T17:52:38Z","cross_cats_sorted":[],"title_canon_sha256":"9888d577b18fba52837e885274fa801347721e8c6729c0f804479b705a858081","abstract_canon_sha256":"cf5e91f859fbc6f28dfee993f06656843b7ac6e21ba7dd87810048dd602f6434"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:48.114767Z","signature_b64":"y2VdP53sBw3UGQoYWtX6C7LlGpQBKLv5oxXMrj8WU9LrAf9GaqQPag8ZQXU3+l6t8t9TLuUP++JuHbxsQ/TBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20b00cfe2cfa932b3b71df303dc70edd1f1781700ed6e6b08bbaeb966fedf65f","last_reissued_at":"2026-07-05T02:34:48.114392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:48.114392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Mutian Xu, Runyu Ding, Xiaojuan Qi","submitted_at":"2021-03-26T17:52:38Z","abstract_excerpt":"We introduce Position Adaptive Convolution (PAConv), a generic convolution operation for 3D point cloud processing. The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet. In this way, the kernel is built in a data-driven manner, endowing PAConv with more flexibility than 2D convolutions to better handle the irregular and unordered point cloud data. Besides, the complexity of the learning process is reduced by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14635","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/2103.14635/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":"2103.14635","created_at":"2026-07-05T02:34:48.114441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14635v2","created_at":"2026-07-05T02:34:48.114441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14635","created_at":"2026-07-05T02:34:48.114441+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECYAZ7RM7KJS","created_at":"2026-07-05T02:34:48.114441+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECYAZ7RM7KJSWO3R","created_at":"2026-07-05T02:34:48.114441+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECYAZ7RM","created_at":"2026-07-05T02:34:48.114441+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/ECYAZ7RM7KJSWO3R34YD3RYO3U","json":"https://pith.science/pith/ECYAZ7RM7KJSWO3R34YD3RYO3U.json","graph_json":"https://pith.science/api/pith-number/ECYAZ7RM7KJSWO3R34YD3RYO3U/graph.json","events_json":"https://pith.science/api/pith-number/ECYAZ7RM7KJSWO3R34YD3RYO3U/events.json","paper":"https://pith.science/paper/ECYAZ7RM"},"agent_actions":{"view_html":"https://pith.science/pith/ECYAZ7RM7KJSWO3R34YD3RYO3U","download_json":"https://pith.science/pith/ECYAZ7RM7KJSWO3R34YD3RYO3U.json","view_paper":"https://pith.science/paper/ECYAZ7RM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14635&json=true","fetch_graph":"https://pith.science/api/pith-number/ECYAZ7RM7KJSWO3R34YD3RYO3U/graph.json","fetch_events":"https://pith.science/api/pith-number/ECYAZ7RM7KJSWO3R34YD3RYO3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECYAZ7RM7KJSWO3R34YD3RYO3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECYAZ7RM7KJSWO3R34YD3RYO3U/action/storage_attestation","attest_author":"https://pith.science/pith/ECYAZ7RM7KJSWO3R34YD3RYO3U/action/author_attestation","sign_citation":"https://pith.science/pith/ECYAZ7RM7KJSWO3R34YD3RYO3U/action/citation_signature","submit_replication":"https://pith.science/pith/ECYAZ7RM7KJSWO3R34YD3RYO3U/action/replication_record"}},"created_at":"2026-07-05T02:34:48.114441+00:00","updated_at":"2026-07-05T02:34:48.114441+00:00"}