{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JPMXLYYN5BBLCMVLLCXT7ZAUIB","short_pith_number":"pith:JPMXLYYN","schema_version":"1.0","canonical_sha256":"4bd975e30de842b132ab58af3fe414404b1892ca23b24c5ce074b44d402e5ea0","source":{"kind":"arxiv","id":"2306.05239","version":3},"attestation_state":"computed","paper":{"title":"Point-Voxel Absorbing Graph Representation Learning for Event Stream based Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Bo Jiang, Chengguo Yuan, Jin Tang, Xiao Wang, Yuxiang Zhang","submitted_at":"2023-06-08T14:38:43Z","abstract_excerpt":"Sampled point and voxel methods are usually employed to downsample the dense events into sparse ones. After that, one popular way is to leverage a graph model which treats the sparse points/voxels as nodes and adopts graph neural networks (GNNs) to learn the representation of event data. Although good performance can be obtained, however, their results are still limited mainly due to two issues. (1) Existing event GNNs generally adopt the additional max (or mean) pooling layer to summarize all node embeddings into a single graph-level representation for the whole event data representation. How"},"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":"2306.05239","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T14:38:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"b60e40f7621f0ce765442072b7ead801d27de84c8b604a630387e69b42d441d3","abstract_canon_sha256":"0c37b16c414c36587ff92fdd3a018054a59b82f446f93a6106712ec973015bf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:18.096593Z","signature_b64":"1tSbm1uhIUJALQuvD3IaCZ9jTgJx0dYrmu7hBG2I79V+tlrBN7UEbsGHg9N3ZtZGV9G1pEwtCMcbxn0U3nhlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd975e30de842b132ab58af3fe414404b1892ca23b24c5ce074b44d402e5ea0","last_reissued_at":"2026-06-24T01:14:18.096038Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:18.096038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Point-Voxel Absorbing Graph Representation Learning for Event Stream based Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Bo Jiang, Chengguo Yuan, Jin Tang, Xiao Wang, Yuxiang Zhang","submitted_at":"2023-06-08T14:38:43Z","abstract_excerpt":"Sampled point and voxel methods are usually employed to downsample the dense events into sparse ones. After that, one popular way is to leverage a graph model which treats the sparse points/voxels as nodes and adopts graph neural networks (GNNs) to learn the representation of event data. Although good performance can be obtained, however, their results are still limited mainly due to two issues. (1) Existing event GNNs generally adopt the additional max (or mean) pooling layer to summarize all node embeddings into a single graph-level representation for the whole event data representation. How"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05239","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/2306.05239/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":"2306.05239","created_at":"2026-06-24T01:14:18.096124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05239v3","created_at":"2026-06-24T01:14:18.096124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05239","created_at":"2026-06-24T01:14:18.096124+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPMXLYYN5BBL","created_at":"2026-06-24T01:14:18.096124+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPMXLYYN5BBLCMVL","created_at":"2026-06-24T01:14:18.096124+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPMXLYYN","created_at":"2026-06-24T01:14:18.096124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.08236","citing_title":"TVTA: Trajectory-Aware Viseme-Guided Temporal Aggregation for Event-Based Lip Reading","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2411.18328","citing_title":"EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB","json":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB.json","graph_json":"https://pith.science/api/pith-number/JPMXLYYN5BBLCMVLLCXT7ZAUIB/graph.json","events_json":"https://pith.science/api/pith-number/JPMXLYYN5BBLCMVLLCXT7ZAUIB/events.json","paper":"https://pith.science/paper/JPMXLYYN"},"agent_actions":{"view_html":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB","download_json":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB.json","view_paper":"https://pith.science/paper/JPMXLYYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05239&json=true","fetch_graph":"https://pith.science/api/pith-number/JPMXLYYN5BBLCMVLLCXT7ZAUIB/graph.json","fetch_events":"https://pith.science/api/pith-number/JPMXLYYN5BBLCMVLLCXT7ZAUIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB/action/storage_attestation","attest_author":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB/action/author_attestation","sign_citation":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB/action/citation_signature","submit_replication":"https://pith.science/pith/JPMXLYYN5BBLCMVLLCXT7ZAUIB/action/replication_record"}},"created_at":"2026-06-24T01:14:18.096124+00:00","updated_at":"2026-06-24T01:14:18.096124+00:00"}