{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VM24PSFCSBSKS2DPXVGOJNFL6J","short_pith_number":"pith:VM24PSFC","canonical_record":{"source":{"id":"2110.09783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T07:55:47Z","cross_cats_sorted":[],"title_canon_sha256":"7ebb172d62cfeedbd40e8a22a1da8b28e9c0368ba16ec75a57ea0e20311cf120","abstract_canon_sha256":"5e21d80436976d192c8e9a2193a8ad0616d531b1614b5865c296c53abbebfc7d"},"schema_version":"1.0"},"canonical_sha256":"ab35c7c8a29064a9686fbd4ce4b4abf25a6704916a0596c040255a8c39547f91","source":{"kind":"arxiv","id":"2110.09783","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09783","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09783v1","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09783","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"VM24PSFCSBSK","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"VM24PSFCSBSKS2DP","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"VM24PSFC","created_at":"2026-07-05T03:23:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VM24PSFCSBSKS2DPXVGOJNFL6J","target":"record","payload":{"canonical_record":{"source":{"id":"2110.09783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T07:55:47Z","cross_cats_sorted":[],"title_canon_sha256":"7ebb172d62cfeedbd40e8a22a1da8b28e9c0368ba16ec75a57ea0e20311cf120","abstract_canon_sha256":"5e21d80436976d192c8e9a2193a8ad0616d531b1614b5865c296c53abbebfc7d"},"schema_version":"1.0"},"canonical_sha256":"ab35c7c8a29064a9686fbd4ce4b4abf25a6704916a0596c040255a8c39547f91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:58.987233Z","signature_b64":"/eMmr+IH0+5PzGtgis44LjkiGRFbG3/bgIiGoBEfx5EC2LGHHlaCV2ELyWltWqSOxh0UydhpF/250OMaJJA/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab35c7c8a29064a9686fbd4ce4b4abf25a6704916a0596c040255a8c39547f91","last_reissued_at":"2026-07-05T03:23:58.986776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:58.986776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.09783","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":"2026-07-05T03:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AwMKOqnDCFC+2bZmTurBzVPu5duOMXcX9GWLd2XDJsvXaFEcZM3mZiubawzjbfn/82vGUhUBGKmlbeUIQzgeDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:19:06.260951Z"},"content_sha256":"ccda77cd2bb337a919b6bdcd0d10817c7b6b1c4fda929034e4a7a9cf6a05127d","schema_version":"1.0","event_id":"sha256:ccda77cd2bb337a919b6bdcd0d10817c7b6b1c4fda929034e4a7a9cf6a05127d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VM24PSFCSBSKS2DPXVGOJNFL6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Liu, Qiuhong Ke, Tingting Xie, Yimin Wei, Yulan Guo","submitted_at":"2021-10-19T07:55:47Z","abstract_excerpt":"Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recognition. In this paper, we propose a novel framework named Point Spatial-Temporal Transformer (PST2) to learn spatial-temporal representations from dynamic 3D point cloud sequences. Our PST2 consists of two major modules: a Spatio-Temporal Self-Attention (STSA) module and a Resolution Embedding (RE) module. Our STSA module is introduced to capture the spatial-temporal context information across adjacent frames, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09783","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/2110.09783/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":"2026-07-05T03:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z6NZad3mYBTeNgaZitdJCGT4STechy+MHhumK3q89vmlMRV4GSG889YOPxBFU6tT1yJlrrS03QNf3IG2N72sCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:19:06.261884Z"},"content_sha256":"e552bf23f9ebf6868ed9507870e4fadac29db84e9777c6a79cf02a6b4392fbae","schema_version":"1.0","event_id":"sha256:e552bf23f9ebf6868ed9507870e4fadac29db84e9777c6a79cf02a6b4392fbae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/bundle.json","state_url":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/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":"2026-08-06T01:19:06Z","links":{"resolver":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J","bundle":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/bundle.json","state":"https://pith.science/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VM24PSFCSBSKS2DPXVGOJNFL6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VM24PSFCSBSKS2DPXVGOJNFL6J","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":"5e21d80436976d192c8e9a2193a8ad0616d531b1614b5865c296c53abbebfc7d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T07:55:47Z","title_canon_sha256":"7ebb172d62cfeedbd40e8a22a1da8b28e9c0368ba16ec75a57ea0e20311cf120"},"schema_version":"1.0","source":{"id":"2110.09783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09783","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09783v1","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09783","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"VM24PSFCSBSK","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"VM24PSFCSBSKS2DP","created_at":"2026-07-05T03:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"VM24PSFC","created_at":"2026-07-05T03:23:58Z"}],"graph_snapshots":[{"event_id":"sha256:e552bf23f9ebf6868ed9507870e4fadac29db84e9777c6a79cf02a6b4392fbae","target":"graph","created_at":"2026-07-05T03:23:58Z","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/2110.09783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective learning of spatial-temporal information within a point cloud sequence is highly important for many down-stream tasks such as 4D semantic segmentation and 3D action recognition. In this paper, we propose a novel framework named Point Spatial-Temporal Transformer (PST2) to learn spatial-temporal representations from dynamic 3D point cloud sequences. Our PST2 consists of two major modules: a Spatio-Temporal Self-Attention (STSA) module and a Resolution Embedding (RE) module. Our STSA module is introduced to capture the spatial-temporal context information across adjacent frames, while ","authors_text":"Hao Liu, Qiuhong Ke, Tingting Xie, Yimin Wei, Yulan Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T07:55:47Z","title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09783","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:ccda77cd2bb337a919b6bdcd0d10817c7b6b1c4fda929034e4a7a9cf6a05127d","target":"record","created_at":"2026-07-05T03:23:58Z","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":"5e21d80436976d192c8e9a2193a8ad0616d531b1614b5865c296c53abbebfc7d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-19T07:55:47Z","title_canon_sha256":"7ebb172d62cfeedbd40e8a22a1da8b28e9c0368ba16ec75a57ea0e20311cf120"},"schema_version":"1.0","source":{"id":"2110.09783","kind":"arxiv","version":1}},"canonical_sha256":"ab35c7c8a29064a9686fbd4ce4b4abf25a6704916a0596c040255a8c39547f91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab35c7c8a29064a9686fbd4ce4b4abf25a6704916a0596c040255a8c39547f91","first_computed_at":"2026-07-05T03:23:58.986776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:58.986776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/eMmr+IH0+5PzGtgis44LjkiGRFbG3/bgIiGoBEfx5EC2LGHHlaCV2ELyWltWqSOxh0UydhpF/250OMaJJA/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:58.987233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.09783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccda77cd2bb337a919b6bdcd0d10817c7b6b1c4fda929034e4a7a9cf6a05127d","sha256:e552bf23f9ebf6868ed9507870e4fadac29db84e9777c6a79cf02a6b4392fbae"],"state_sha256":"5d54341247ce00faab49833b601132ca12e0216c1ce4f5308175af62f1eb33b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zYJ1U43Wfec3GfXFBLoSOZCTE43ZzW61fN6jWr13b6MMlz73zFz/Bh0vu5KonRu/6Gfw2JAECUcMht/jeqmEAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:19:06.269762Z","bundle_sha256":"4d32d97c844a8a0f90662b7d28966bb53ff8c503b2ae7dab9cfb33eca0782ac0"}}