{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KGEZZCELWQ6HLFQ4NAQATNMP76","short_pith_number":"pith:KGEZZCEL","schema_version":"1.0","canonical_sha256":"51899c888bb43c75961c682009b58fffa926f2cb81dc3101db9762fd13008707","source":{"kind":"arxiv","id":"2605.20150","version":1},"attestation_state":"computed","paper":{"title":"TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.CV","authors_text":"Binhang Yuan, Chaojian Li, Chonghao Zhong, Hao Zhao, Hua Chen, Linfeng Shi, Tiecheng Sun","submitted_at":"2026-05-19T17:40:59Z","abstract_excerpt":"Training 3D Gaussian Splatting (3DGS) at billion-primitive scale is fundamentally memory-bound: each Gaussian primitive carries a large attribute vector, and the aggregate parameter table quickly exceeds GPU capacity, limiting prior systems to tens of millions of Gaussians on commodity single-GPU hardware. We observe that 3DGS training is inherently sparse and trajectory-conditioned: each iteration activates only the Gaussians visible from the current camera batch, so GPU memory can serve as a working-set cache rather than a persistent parameter store. Building on this insight, we introduce Ti"},"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":"2605.20150","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T17:40:59Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"c4626d73145dc8c15e375f74353ea9fdfc5ad5a352c270ae034917f6088cbaa7","abstract_canon_sha256":"aed19b1d452eab242c8d2cf4e313994e77f6519389aa138bc818b2f551c3b76c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:06:04.379508Z","signature_b64":"IrM5fpqXSkW41pKX71kDQ91SC4hgV30FIzZs9tJmBkcrLw5wbD3XYwra5wLNYmy20wJ4KmHuz6s72p9mexoBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51899c888bb43c75961c682009b58fffa926f2cb81dc3101db9762fd13008707","last_reissued_at":"2026-05-20T02:06:04.378797Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:06:04.378797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.CV","authors_text":"Binhang Yuan, Chaojian Li, Chonghao Zhong, Hao Zhao, Hua Chen, Linfeng Shi, Tiecheng Sun","submitted_at":"2026-05-19T17:40:59Z","abstract_excerpt":"Training 3D Gaussian Splatting (3DGS) at billion-primitive scale is fundamentally memory-bound: each Gaussian primitive carries a large attribute vector, and the aggregate parameter table quickly exceeds GPU capacity, limiting prior systems to tens of millions of Gaussians on commodity single-GPU hardware. We observe that 3DGS training is inherently sparse and trajectory-conditioned: each iteration activates only the Gaussians visible from the current camera batch, so GPU memory can serve as a working-set cache rather than a persistent parameter store. Building on this insight, we introduce Ti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20150","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/2605.20150/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":"2605.20150","created_at":"2026-05-20T02:06:04.378907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20150v1","created_at":"2026-05-20T02:06:04.378907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20150","created_at":"2026-05-20T02:06:04.378907+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGEZZCELWQ6H","created_at":"2026-05-20T02:06:04.378907+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGEZZCELWQ6HLFQ4","created_at":"2026-05-20T02:06:04.378907+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGEZZCEL","created_at":"2026-05-20T02:06:04.378907+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/KGEZZCELWQ6HLFQ4NAQATNMP76","json":"https://pith.science/pith/KGEZZCELWQ6HLFQ4NAQATNMP76.json","graph_json":"https://pith.science/api/pith-number/KGEZZCELWQ6HLFQ4NAQATNMP76/graph.json","events_json":"https://pith.science/api/pith-number/KGEZZCELWQ6HLFQ4NAQATNMP76/events.json","paper":"https://pith.science/paper/KGEZZCEL"},"agent_actions":{"view_html":"https://pith.science/pith/KGEZZCELWQ6HLFQ4NAQATNMP76","download_json":"https://pith.science/pith/KGEZZCELWQ6HLFQ4NAQATNMP76.json","view_paper":"https://pith.science/paper/KGEZZCEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20150&json=true","fetch_graph":"https://pith.science/api/pith-number/KGEZZCELWQ6HLFQ4NAQATNMP76/graph.json","fetch_events":"https://pith.science/api/pith-number/KGEZZCELWQ6HLFQ4NAQATNMP76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGEZZCELWQ6HLFQ4NAQATNMP76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGEZZCELWQ6HLFQ4NAQATNMP76/action/storage_attestation","attest_author":"https://pith.science/pith/KGEZZCELWQ6HLFQ4NAQATNMP76/action/author_attestation","sign_citation":"https://pith.science/pith/KGEZZCELWQ6HLFQ4NAQATNMP76/action/citation_signature","submit_replication":"https://pith.science/pith/KGEZZCELWQ6HLFQ4NAQATNMP76/action/replication_record"}},"created_at":"2026-05-20T02:06:04.378907+00:00","updated_at":"2026-05-20T02:06:04.378907+00:00"}