{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DBCWPMESAW2TTJ3DNAM6P5P5CM","short_pith_number":"pith:DBCWPMES","canonical_record":{"source":{"id":"1904.03375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-06T06:25:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"901fa19a4a8ee35afcb354386ef5c1d581ed9c83faa4d73a7064995459ad6be8","abstract_canon_sha256":"18f49384615b2df321f5b9ea76dc11fa422ca2c87220404b8bd42a6d280d4a63"},"schema_version":"1.0"},"canonical_sha256":"184567b09205b539a7636819e7f5fd132c21d09a258105a06d5b72cb65a49115","source":{"kind":"arxiv","id":"1904.03375","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03375","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03375v1","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03375","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"DBCWPMESAW2T","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DBCWPMESAW2TTJ3D","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DBCWPMES","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DBCWPMESAW2TTJ3DNAM6P5P5CM","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-06T06:25:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"901fa19a4a8ee35afcb354386ef5c1d581ed9c83faa4d73a7064995459ad6be8","abstract_canon_sha256":"18f49384615b2df321f5b9ea76dc11fa422ca2c87220404b8bd42a6d280d4a63"},"schema_version":"1.0"},"canonical_sha256":"184567b09205b539a7636819e7f5fd132c21d09a258105a06d5b72cb65a49115","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:13.649816Z","signature_b64":"5DIEC1EL80skY26Pk3r/dMcaXIFFEChGH/FHjeOqyfmkDiRxoCQ3KO2hu5Jw7e4M2h2yPT12J3a9SvPzhOlcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"184567b09205b539a7636819e7f5fd132c21d09a258105a06d5b72cb65a49115","last_reissued_at":"2026-05-17T23:49:13.649189Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:13.649189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03375","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":"2026-05-17T23:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G45aST2Ek/BvnwT7ZUJHUWWeBjTyIETvm0QmgOphQZhKrSvMHDbbVRkaAeIe13GITedJl6VbxG8pzTGl7PoSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:52:30.701627Z"},"content_sha256":"218e4f67985ffbafc2f201feb37836e006d648e026a229e9720cbb465b9ed68c","schema_version":"1.0","event_id":"sha256:218e4f67985ffbafc2f201feb37836e006d648e026a229e9720cbb465b9ed68c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DBCWPMESAW2TTJ3DNAM6P5P5CM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Jiancheng Yang, Jinxian Liu, Linguo Li, Mengdie Zhou, Qiang Zhang, Qi Tian","submitted_at":"2019-04-06T06:25:41Z","abstract_excerpt":"Geometric deep learning is increasingly important thanks to the popularity of 3D sensors. Inspired by the recent advances in NLP domain, the self-attention transformer is introduced to consume the point clouds. We develop Point Attention Transformers (PATs), using a parameter-efficient Group Shuffle Attention (GSA) to replace the costly Multi-Head Attention. We demonstrate its ability to process size-varying inputs, and prove its permutation equivariance. Besides, prior work uses heuristics dependence on the input data (e.g., Furthest Point Sampling) to hierarchically select subsets of input p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03375","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":""},"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":"2026-05-17T23:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3e1pUSJHzpsfprr+bqiXd1a7x2TFbuF/NxflWmNG2sObzhPWBgWBMVa3leWVeOtAksGKKd7v6ebmK9xDjTEoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:52:30.702139Z"},"content_sha256":"9c93946c4bd0802efcd34d48d7bdca45ff6145efef323289868481b68bf0a147","schema_version":"1.0","event_id":"sha256:9c93946c4bd0802efcd34d48d7bdca45ff6145efef323289868481b68bf0a147"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBCWPMESAW2TTJ3DNAM6P5P5CM/bundle.json","state_url":"https://pith.science/pith/DBCWPMESAW2TTJ3DNAM6P5P5CM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBCWPMESAW2TTJ3DNAM6P5P5CM/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":"2026-08-04T20:52:30Z","links":{"resolver":"https://pith.science/pith/DBCWPMESAW2TTJ3DNAM6P5P5CM","bundle":"https://pith.science/pith/DBCWPMESAW2TTJ3DNAM6P5P5CM/bundle.json","state":"https://pith.science/pith/DBCWPMESAW2TTJ3DNAM6P5P5CM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBCWPMESAW2TTJ3DNAM6P5P5CM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DBCWPMESAW2TTJ3DNAM6P5P5CM","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":"18f49384615b2df321f5b9ea76dc11fa422ca2c87220404b8bd42a6d280d4a63","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-06T06:25:41Z","title_canon_sha256":"901fa19a4a8ee35afcb354386ef5c1d581ed9c83faa4d73a7064995459ad6be8"},"schema_version":"1.0","source":{"id":"1904.03375","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03375","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03375v1","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03375","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"DBCWPMESAW2T","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DBCWPMESAW2TTJ3D","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DBCWPMES","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:9c93946c4bd0802efcd34d48d7bdca45ff6145efef323289868481b68bf0a147","target":"graph","created_at":"2026-05-17T23:49:13Z","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"},"paper":{"abstract_excerpt":"Geometric deep learning is increasingly important thanks to the popularity of 3D sensors. Inspired by the recent advances in NLP domain, the self-attention transformer is introduced to consume the point clouds. We develop Point Attention Transformers (PATs), using a parameter-efficient Group Shuffle Attention (GSA) to replace the costly Multi-Head Attention. We demonstrate its ability to process size-varying inputs, and prove its permutation equivariance. Besides, prior work uses heuristics dependence on the input data (e.g., Furthest Point Sampling) to hierarchically select subsets of input p","authors_text":"Bingbing Ni, Jiancheng Yang, Jinxian Liu, Linguo Li, Mengdie Zhou, Qiang Zhang, Qi Tian","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-06T06:25:41Z","title":"Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03375","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":"sha256:218e4f67985ffbafc2f201feb37836e006d648e026a229e9720cbb465b9ed68c","target":"record","created_at":"2026-05-17T23:49:13Z","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":"18f49384615b2df321f5b9ea76dc11fa422ca2c87220404b8bd42a6d280d4a63","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-06T06:25:41Z","title_canon_sha256":"901fa19a4a8ee35afcb354386ef5c1d581ed9c83faa4d73a7064995459ad6be8"},"schema_version":"1.0","source":{"id":"1904.03375","kind":"arxiv","version":1}},"canonical_sha256":"184567b09205b539a7636819e7f5fd132c21d09a258105a06d5b72cb65a49115","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"184567b09205b539a7636819e7f5fd132c21d09a258105a06d5b72cb65a49115","first_computed_at":"2026-05-17T23:49:13.649189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:13.649189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5DIEC1EL80skY26Pk3r/dMcaXIFFEChGH/FHjeOqyfmkDiRxoCQ3KO2hu5Jw7e4M2h2yPT12J3a9SvPzhOlcCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:13.649816Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03375","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:218e4f67985ffbafc2f201feb37836e006d648e026a229e9720cbb465b9ed68c","sha256:9c93946c4bd0802efcd34d48d7bdca45ff6145efef323289868481b68bf0a147"],"state_sha256":"31b16bf1042b6f14d581b69d4af71a67ec3c30d03194e48d2acd168a44d8a109"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhdQA4IyIolIwklHX9tzF90Ik4cuFxr5WOCh/fgrzz6VpO688y8qO6HXn6d4Exq8UElyQnWsqJpIv6oea5ceBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:52:30.705056Z","bundle_sha256":"1c91b37f7764b143b21f6693b056d1fe3180deb2efe8aa024f414e20c4fc22db"}}