{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZRLKMYVFHPHM3SSYD3KHEBMOIL","short_pith_number":"pith:ZRLKMYVF","canonical_record":{"source":{"id":"2104.05706","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T17:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"16ea7f3736a21ac1b924166d3ba806e91c2b1d50d0b042412c142c546ac4b983","abstract_canon_sha256":"af706fa5f99da49ca8cef209d224cf9ee18705febb57b2a0fdb52d0cf539c5df"},"schema_version":"1.0"},"canonical_sha256":"cc56a662a53bcecdca581ed472058e42f8231eab09686640d599a8aefc187345","source":{"kind":"arxiv","id":"2104.05706","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05706","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05706v1","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05706","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZRLKMYVFHPHM","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"ZRLKMYVFHPHM3SSY","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"ZRLKMYVF","created_at":"2026-07-05T02:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZRLKMYVFHPHM3SSYD3KHEBMOIL","target":"record","payload":{"canonical_record":{"source":{"id":"2104.05706","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T17:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"16ea7f3736a21ac1b924166d3ba806e91c2b1d50d0b042412c142c546ac4b983","abstract_canon_sha256":"af706fa5f99da49ca8cef209d224cf9ee18705febb57b2a0fdb52d0cf539c5df"},"schema_version":"1.0"},"canonical_sha256":"cc56a662a53bcecdca581ed472058e42f8231eab09686640d599a8aefc187345","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:15.558448Z","signature_b64":"zogTWutAG2kosZgiZI33XD1i3CP/4s274sGe8T5zGTDDM1VQ/PBR/o0jVjwmG1nojHqV3wqfr42DFDNiVr6IDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc56a662a53bcecdca581ed472058e42f8231eab09686640d599a8aefc187345","last_reissued_at":"2026-07-05T02:31:15.557857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:15.557857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.05706","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CRTVrzmoSXiCT/R3t9HVa67a93HeHfhcw0+bPncVo2tx5ZCc81y87G78Q3DbILUewVXYvQujNI8C/T3fI9OqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T22:48:49.949790Z"},"content_sha256":"815576cfc519204cf46087a6ff37a0bcc42a65ec6d0592200679125dc9ac84fe","schema_version":"1.0","event_id":"sha256:815576cfc519204cf46087a6ff37a0bcc42a65ec6d0592200679125dc9ac84fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZRLKMYVFHPHM3SSYD3KHEBMOIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Efficient Graph Convolutional Networks for Point Cloud Handling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gregory Chirikjian, He Chen, Luc Van Gool, Marc Pollefeys, Radu Timofte, Yawei Li, Zhaopeng Cui","submitted_at":"2021-04-12T17:59:16Z","abstract_excerpt":"In this paper, we aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds. The basic graph convolution that is typically composed of a $K$-nearest neighbor (KNN) search and a multilayer perceptron (MLP) is examined. By mathematically analyzing the operations there, two findings to improve the efficiency of GCNs are obtained. (1) The local geometric structure information of 3D representations propagates smoothly across the GCN that relies on KNN search to gather neighborhood features. This motivates the simplification of multiple KNN sea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05706","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/2104.05706/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"okrxl4+y744NAwqjR//xrYlmV+nltDkPbmZvfV4FqjCaw8HdOK4UqTPlFWAnPm5Q+2xTgZd5NDZ0i/whHD8mCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T22:48:49.950173Z"},"content_sha256":"e142e6b2e5c954c913f0f15b8f86a840bd70ce24c838c5587123405daf83ab91","schema_version":"1.0","event_id":"sha256:e142e6b2e5c954c913f0f15b8f86a840bd70ce24c838c5587123405daf83ab91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZRLKMYVFHPHM3SSYD3KHEBMOIL/bundle.json","state_url":"https://pith.science/pith/ZRLKMYVFHPHM3SSYD3KHEBMOIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZRLKMYVFHPHM3SSYD3KHEBMOIL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-27T22:48:49Z","links":{"resolver":"https://pith.science/pith/ZRLKMYVFHPHM3SSYD3KHEBMOIL","bundle":"https://pith.science/pith/ZRLKMYVFHPHM3SSYD3KHEBMOIL/bundle.json","state":"https://pith.science/pith/ZRLKMYVFHPHM3SSYD3KHEBMOIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZRLKMYVFHPHM3SSYD3KHEBMOIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZRLKMYVFHPHM3SSYD3KHEBMOIL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"af706fa5f99da49ca8cef209d224cf9ee18705febb57b2a0fdb52d0cf539c5df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T17:59:16Z","title_canon_sha256":"16ea7f3736a21ac1b924166d3ba806e91c2b1d50d0b042412c142c546ac4b983"},"schema_version":"1.0","source":{"id":"2104.05706","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05706","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05706v1","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05706","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZRLKMYVFHPHM","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"ZRLKMYVFHPHM3SSY","created_at":"2026-07-05T02:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"ZRLKMYVF","created_at":"2026-07-05T02:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:e142e6b2e5c954c913f0f15b8f86a840bd70ce24c838c5587123405daf83ab91","target":"graph","created_at":"2026-07-05T02:31:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.05706/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds. The basic graph convolution that is typically composed of a $K$-nearest neighbor (KNN) search and a multilayer perceptron (MLP) is examined. By mathematically analyzing the operations there, two findings to improve the efficiency of GCNs are obtained. (1) The local geometric structure information of 3D representations propagates smoothly across the GCN that relies on KNN search to gather neighborhood features. This motivates the simplification of multiple KNN sea","authors_text":"Gregory Chirikjian, He Chen, Luc Van Gool, Marc Pollefeys, Radu Timofte, Yawei Li, Zhaopeng Cui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T17:59:16Z","title":"Towards Efficient Graph Convolutional Networks for Point Cloud Handling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05706","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:815576cfc519204cf46087a6ff37a0bcc42a65ec6d0592200679125dc9ac84fe","target":"record","created_at":"2026-07-05T02:31:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"af706fa5f99da49ca8cef209d224cf9ee18705febb57b2a0fdb52d0cf539c5df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T17:59:16Z","title_canon_sha256":"16ea7f3736a21ac1b924166d3ba806e91c2b1d50d0b042412c142c546ac4b983"},"schema_version":"1.0","source":{"id":"2104.05706","kind":"arxiv","version":1}},"canonical_sha256":"cc56a662a53bcecdca581ed472058e42f8231eab09686640d599a8aefc187345","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc56a662a53bcecdca581ed472058e42f8231eab09686640d599a8aefc187345","first_computed_at":"2026-07-05T02:31:15.557857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:15.557857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zogTWutAG2kosZgiZI33XD1i3CP/4s274sGe8T5zGTDDM1VQ/PBR/o0jVjwmG1nojHqV3wqfr42DFDNiVr6IDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:15.558448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.05706","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:815576cfc519204cf46087a6ff37a0bcc42a65ec6d0592200679125dc9ac84fe","sha256:e142e6b2e5c954c913f0f15b8f86a840bd70ce24c838c5587123405daf83ab91"],"state_sha256":"d8d9c3eef152f4d2ae9521bdd1a2cb2fb6088bf3af85ff6ec60c7777efb5e120"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dxh6/0NLmSSgcb9FrMNmWZY71dGTlL0zFu1eZDkvQSCSddn4JliNvwyARs4dLeLxPIwci0Bb+vwb/yK1F6ysAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T22:48:49.952794Z","bundle_sha256":"0fe26fc6c59dfe57490acdbadf83a75c2209770a8fc1569a41f788ba1a1fa2ab"}}