{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BP3GAURF3MWRMOGV4OAMW5ON4R","short_pith_number":"pith:BP3GAURF","canonical_record":{"source":{"id":"2111.00207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-30T08:39:55Z","cross_cats_sorted":[],"title_canon_sha256":"406b3553f3ebb4e54cd4a340df153ebb8996f56759de512f5f705f198ed7327c","abstract_canon_sha256":"ada24cc75a97f8dd84ac6e69baee21cd2387c5014d191faaa826658bc7ca2a37"},"schema_version":"1.0"},"canonical_sha256":"0bf6605225db2d1638d5e380cb75cde47832c813f3eeff0aad1a7193456888ff","source":{"kind":"arxiv","id":"2111.00207","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00207","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00207v3","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00207","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"BP3GAURF3MWR","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"BP3GAURF3MWRMOGV","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"BP3GAURF","created_at":"2026-07-05T04:08:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BP3GAURF3MWRMOGV4OAMW5ON4R","target":"record","payload":{"canonical_record":{"source":{"id":"2111.00207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-30T08:39:55Z","cross_cats_sorted":[],"title_canon_sha256":"406b3553f3ebb4e54cd4a340df153ebb8996f56759de512f5f705f198ed7327c","abstract_canon_sha256":"ada24cc75a97f8dd84ac6e69baee21cd2387c5014d191faaa826658bc7ca2a37"},"schema_version":"1.0"},"canonical_sha256":"0bf6605225db2d1638d5e380cb75cde47832c813f3eeff0aad1a7193456888ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:16.822326Z","signature_b64":"qVuP76Hjd4Jv/DcDSfzaiJg93uQan2wjoEaJ/chsWCYYclsPK0nrGlSmbr6omEXVy2s4VNWj2cXLe2dobXSLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf6605225db2d1638d5e380cb75cde47832c813f3eeff0aad1a7193456888ff","last_reissued_at":"2026-07-05T04:08:16.821872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:16.821872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.00207","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fzDn7j9LhpRBOwqb9fW1rObB1JoUfs5HKRCTEARFnwZhRVHzHQskuV7WVzllnb4jXvlqbe8cmn9WJHb8BDgrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:44:57.511430Z"},"content_sha256":"5d8a73489f04d631bcd51c9dfaaf9a3ae0bff74cecc5059d9b62aa63b9b8508f","schema_version":"1.0","event_id":"sha256:5d8a73489f04d631bcd51c9dfaaf9a3ae0bff74cecc5059d9b62aa63b9b8508f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BP3GAURF3MWRMOGV4OAMW5ON4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PatchFormer: An Efficient Point Transformer with Patch Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haocheng Wan, Xinyi Shen, Zhang Cheng, Zizhao Wu","submitted_at":"2021-10-30T08:39:55Z","abstract_excerpt":"The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are computationally expensive since they need to generate a large attention map, which has quadratic complexity (both in space and time) with respect to input size. To solve this shortcoming, we introduce Patch ATtention (PAT) to adaptively learn a much smaller set of bases upon which the attention maps are computed. By a weighted summation upon these bases, PAT not only ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00207","kind":"arxiv","version":3},"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/2111.00207/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":"2026-07-05T04:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YFYksb4gepcMRHlAR59O0VG/SEhMy+tyZvbEDPyDCdV+iKJUKoj8bzg4zt02fJG5P2jfrMBTxVkTr0B7nhufCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:44:57.511908Z"},"content_sha256":"8f3acd3be25f42a6410a71f79636d43404683a61e620e3f8574fac8a9d1e0b74","schema_version":"1.0","event_id":"sha256:8f3acd3be25f42a6410a71f79636d43404683a61e620e3f8574fac8a9d1e0b74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BP3GAURF3MWRMOGV4OAMW5ON4R/bundle.json","state_url":"https://pith.science/pith/BP3GAURF3MWRMOGV4OAMW5ON4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BP3GAURF3MWRMOGV4OAMW5ON4R/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":"2026-08-09T18:44:57Z","links":{"resolver":"https://pith.science/pith/BP3GAURF3MWRMOGV4OAMW5ON4R","bundle":"https://pith.science/pith/BP3GAURF3MWRMOGV4OAMW5ON4R/bundle.json","state":"https://pith.science/pith/BP3GAURF3MWRMOGV4OAMW5ON4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BP3GAURF3MWRMOGV4OAMW5ON4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BP3GAURF3MWRMOGV4OAMW5ON4R","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":"ada24cc75a97f8dd84ac6e69baee21cd2387c5014d191faaa826658bc7ca2a37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-30T08:39:55Z","title_canon_sha256":"406b3553f3ebb4e54cd4a340df153ebb8996f56759de512f5f705f198ed7327c"},"schema_version":"1.0","source":{"id":"2111.00207","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00207","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00207v3","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00207","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"BP3GAURF3MWR","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"BP3GAURF3MWRMOGV","created_at":"2026-07-05T04:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"BP3GAURF","created_at":"2026-07-05T04:08:16Z"}],"graph_snapshots":[{"event_id":"sha256:8f3acd3be25f42a6410a71f79636d43404683a61e620e3f8574fac8a9d1e0b74","target":"graph","created_at":"2026-07-05T04:08:16Z","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/2111.00207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are computationally expensive since they need to generate a large attention map, which has quadratic complexity (both in space and time) with respect to input size. To solve this shortcoming, we introduce Patch ATtention (PAT) to adaptively learn a much smaller set of bases upon which the attention maps are computed. By a weighted summation upon these bases, PAT not only ca","authors_text":"Haocheng Wan, Xinyi Shen, Zhang Cheng, Zizhao Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-30T08:39:55Z","title":"PatchFormer: An Efficient Point Transformer with Patch Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00207","kind":"arxiv","version":3},"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":"sha256:5d8a73489f04d631bcd51c9dfaaf9a3ae0bff74cecc5059d9b62aa63b9b8508f","target":"record","created_at":"2026-07-05T04:08:16Z","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":"ada24cc75a97f8dd84ac6e69baee21cd2387c5014d191faaa826658bc7ca2a37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-30T08:39:55Z","title_canon_sha256":"406b3553f3ebb4e54cd4a340df153ebb8996f56759de512f5f705f198ed7327c"},"schema_version":"1.0","source":{"id":"2111.00207","kind":"arxiv","version":3}},"canonical_sha256":"0bf6605225db2d1638d5e380cb75cde47832c813f3eeff0aad1a7193456888ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf6605225db2d1638d5e380cb75cde47832c813f3eeff0aad1a7193456888ff","first_computed_at":"2026-07-05T04:08:16.821872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:16.821872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qVuP76Hjd4Jv/DcDSfzaiJg93uQan2wjoEaJ/chsWCYYclsPK0nrGlSmbr6omEXVy2s4VNWj2cXLe2dobXSLAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:16.822326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00207","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d8a73489f04d631bcd51c9dfaaf9a3ae0bff74cecc5059d9b62aa63b9b8508f","sha256:8f3acd3be25f42a6410a71f79636d43404683a61e620e3f8574fac8a9d1e0b74"],"state_sha256":"22ae5e95be89a5def78851406946636890e82fe1e2ddab03bddbca00a31db66b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z0lBbXe7pUm+wAJffL0iKESnWGVVqoN5I4I9AHRoK51qfZ06rsdRx2hXfNCKqSSA1CBNtN8q0ZndUiiPHefVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:44:57.515398Z","bundle_sha256":"b05234a1a462f976a4afc979a3068fb05dfe6ccd765f584b1b7f37c7ae051686"}}