{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VQVZXJF3FBA4DPKDF2QG3C6LNG","short_pith_number":"pith:VQVZXJF3","schema_version":"1.0","canonical_sha256":"ac2b9ba4bb2841c1bd432ea06d8bcb69b9ec13db9fcd33f02f11f0f4c0aa4ce7","source":{"kind":"arxiv","id":"2601.17354","version":5},"attestation_state":"computed","paper":{"title":"PocketGS: On-Device Training of 3D Gaussian Splatting for High Perceptual Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Bing Wang, Guangchi Fang, Shu Yang, Wenzhi Guo","submitted_at":"2026-01-24T07:58:53Z","abstract_excerpt":"While 3D Gaussian Splatting (3DGS) enables real-time rendering, its training demands workstation-level compute and memory, making mobile deployment impractical under minute-scale time budgets and limited peak memory. We present PocketGS, a mobile scene modeling paradigm that enables on-device 3DGS training under these tightly coupled constraints while preserving high-fidelity reconstruction. PocketGS resolves the fundamental tension between training efficiency, memory compactness, and modeling quality through three co-designed operators: $\\mathcal{G}$ builds geometry-faithful point-cloud prior"},"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":"2601.17354","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-24T07:58:53Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"b9ddd45ef2f5dd29d3b62fcf403b34b6e25ac642b9a9242bd328a2254a659275","abstract_canon_sha256":"25aaa7e8fa75fe23ca719462560c168462730c799236472acc296ac7f55aaa02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:35.522659Z","signature_b64":"0IARF8Mbm7749PNT7U60zCXuqntK+3uTkwE1WgJp2bke5nRUDCn9aHmHoy+AXEfIbQwt3ZaeQaMtzsZONAhcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac2b9ba4bb2841c1bd432ea06d8bcb69b9ec13db9fcd33f02f11f0f4c0aa4ce7","last_reissued_at":"2026-05-28T01:04:35.522167Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:35.522167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PocketGS: On-Device Training of 3D Gaussian Splatting for High Perceptual Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Bing Wang, Guangchi Fang, Shu Yang, Wenzhi Guo","submitted_at":"2026-01-24T07:58:53Z","abstract_excerpt":"While 3D Gaussian Splatting (3DGS) enables real-time rendering, its training demands workstation-level compute and memory, making mobile deployment impractical under minute-scale time budgets and limited peak memory. We present PocketGS, a mobile scene modeling paradigm that enables on-device 3DGS training under these tightly coupled constraints while preserving high-fidelity reconstruction. PocketGS resolves the fundamental tension between training efficiency, memory compactness, and modeling quality through three co-designed operators: $\\mathcal{G}$ builds geometry-faithful point-cloud prior"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.17354","kind":"arxiv","version":5},"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/2601.17354/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":"2601.17354","created_at":"2026-05-28T01:04:35.522227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.17354v5","created_at":"2026-05-28T01:04:35.522227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17354","created_at":"2026-05-28T01:04:35.522227+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQVZXJF3FBA4","created_at":"2026-05-28T01:04:35.522227+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQVZXJF3FBA4DPKD","created_at":"2026-05-28T01:04:35.522227+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQVZXJF3","created_at":"2026-05-28T01:04:35.522227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17002","citing_title":"A Single Atlas is All You Need: Decoder-Side Gaussian Splatting for Immersive Video","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG","json":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG.json","graph_json":"https://pith.science/api/pith-number/VQVZXJF3FBA4DPKDF2QG3C6LNG/graph.json","events_json":"https://pith.science/api/pith-number/VQVZXJF3FBA4DPKDF2QG3C6LNG/events.json","paper":"https://pith.science/paper/VQVZXJF3"},"agent_actions":{"view_html":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG","download_json":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG.json","view_paper":"https://pith.science/paper/VQVZXJF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.17354&json=true","fetch_graph":"https://pith.science/api/pith-number/VQVZXJF3FBA4DPKDF2QG3C6LNG/graph.json","fetch_events":"https://pith.science/api/pith-number/VQVZXJF3FBA4DPKDF2QG3C6LNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG/action/storage_attestation","attest_author":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG/action/author_attestation","sign_citation":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG/action/citation_signature","submit_replication":"https://pith.science/pith/VQVZXJF3FBA4DPKDF2QG3C6LNG/action/replication_record"}},"created_at":"2026-05-28T01:04:35.522227+00:00","updated_at":"2026-05-28T01:04:35.522227+00:00"}