{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QLFMAQARIX32MH6A7FBUDTDGLH","short_pith_number":"pith:QLFMAQAR","schema_version":"1.0","canonical_sha256":"82cac0401145f7a61fc0f94341cc6659d09d31a677ba1db1dd12cd1bd0ba5ae4","source":{"kind":"arxiv","id":"2606.18588","version":1},"attestation_state":"computed","paper":{"title":"Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.DC","authors_text":"Ang Li, Bo Fang, Chengming Zhang, Miao Yin, Sheng Di, Stavros Kalafatis, Wei Niu, Wenqi Jia, Ying Huang, Yuede Ji, Yu Gong, Yuke Wang, Zhewen Hu","submitted_at":"2026-06-17T01:27:41Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time.\n  We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global compositi"},"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":"2606.18588","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-17T01:27:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9725f32a621e53217d5a09edcbe2680fb6c381a4ddb9f0104d618dfe1066cf13","abstract_canon_sha256":"a59b24650bec48218acb9a7c60b4bc2de99b4ddcd77c5053401ce0f94cb1c4ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:41.798401Z","signature_b64":"28S6+gNIAKK6XtZVPAq2cZ6TCMsHQOkkjoc7Yvw7A5Zpiggt/k1qEZLNPxoiLBpyL0Z+mg6XWatIUmp7NUndAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82cac0401145f7a61fc0f94341cc6659d09d31a677ba1db1dd12cd1bd0ba5ae4","last_reissued_at":"2026-06-19T16:11:41.798022Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:41.798022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.DC","authors_text":"Ang Li, Bo Fang, Chengming Zhang, Miao Yin, Sheng Di, Stavros Kalafatis, Wei Niu, Wenqi Jia, Ying Huang, Yuede Ji, Yu Gong, Yuke Wang, Zhewen Hu","submitted_at":"2026-06-17T01:27:41Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time.\n  We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global compositi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18588","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/2606.18588/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":"2606.18588","created_at":"2026-06-19T16:11:41.798085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18588v1","created_at":"2026-06-19T16:11:41.798085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18588","created_at":"2026-06-19T16:11:41.798085+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLFMAQARIX32","created_at":"2026-06-19T16:11:41.798085+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLFMAQARIX32MH6A","created_at":"2026-06-19T16:11:41.798085+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLFMAQAR","created_at":"2026-06-19T16:11:41.798085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH","json":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH.json","graph_json":"https://pith.science/api/pith-number/QLFMAQARIX32MH6A7FBUDTDGLH/graph.json","events_json":"https://pith.science/api/pith-number/QLFMAQARIX32MH6A7FBUDTDGLH/events.json","paper":"https://pith.science/paper/QLFMAQAR"},"agent_actions":{"view_html":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH","download_json":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH.json","view_paper":"https://pith.science/paper/QLFMAQAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18588&json=true","fetch_graph":"https://pith.science/api/pith-number/QLFMAQARIX32MH6A7FBUDTDGLH/graph.json","fetch_events":"https://pith.science/api/pith-number/QLFMAQARIX32MH6A7FBUDTDGLH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH/action/storage_attestation","attest_author":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH/action/author_attestation","sign_citation":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH/action/citation_signature","submit_replication":"https://pith.science/pith/QLFMAQARIX32MH6A7FBUDTDGLH/action/replication_record"}},"created_at":"2026-06-19T16:11:41.798085+00:00","updated_at":"2026-06-19T16:11:41.798085+00:00"}