{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3OWG5W7ZZSKDDTNMNIN4KHO2E4","short_pith_number":"pith:3OWG5W7Z","schema_version":"1.0","canonical_sha256":"dbac6edbf9cc9431cdac6a1bc51dda272068b449909a40fae4c75c670baac6b9","source":{"kind":"arxiv","id":"2412.04887","version":2},"attestation_state":"computed","paper":{"title":"Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jixuan Fan, Tianru Dai, Wanhua Li, Yansong Tang, Yifei Han","submitted_at":"2024-12-06T09:31:12Z","abstract_excerpt":"3D Gaussian Splatting has demonstrated notable success in large-scale scene reconstruction, but challenges persist due to high training memory consumption and storage overhead. Hybrid representations that integrate implicit and explicit features offer a way to mitigate these limitations. However, when applied in parallelized block-wise training, two critical issues arise since reconstruction accuracy deteriorates due to reduced data diversity when training each block independently, and parallel training restricts the number of divided blocks to the available number of GPUs. To address these is"},"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":"2412.04887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T09:31:12Z","cross_cats_sorted":[],"title_canon_sha256":"18fd2c00d87d0559a6aee728a64921f39100b1287e42938b1d673e9de5e9c654","abstract_canon_sha256":"289837a65bc03a54bc2694f8f3bcfe61f1d3e016b14b88eb328ae643283efd2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:16.402248Z","signature_b64":"3S5iMipaQ7xCUjOOYziRfF88CYBILfXBMqwsmnBqL3TH3fcykWA98wdAVSDodtE1SKyNmBSyxEQmIb0gspo9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbac6edbf9cc9431cdac6a1bc51dda272068b449909a40fae4c75c670baac6b9","last_reissued_at":"2026-07-05T11:47:16.401587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:16.401587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jixuan Fan, Tianru Dai, Wanhua Li, Yansong Tang, Yifei Han","submitted_at":"2024-12-06T09:31:12Z","abstract_excerpt":"3D Gaussian Splatting has demonstrated notable success in large-scale scene reconstruction, but challenges persist due to high training memory consumption and storage overhead. Hybrid representations that integrate implicit and explicit features offer a way to mitigate these limitations. However, when applied in parallelized block-wise training, two critical issues arise since reconstruction accuracy deteriorates due to reduced data diversity when training each block independently, and parallel training restricts the number of divided blocks to the available number of GPUs. To address these is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04887","kind":"arxiv","version":2},"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/2412.04887/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":"2412.04887","created_at":"2026-07-05T11:47:16.401671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04887v2","created_at":"2026-07-05T11:47:16.401671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04887","created_at":"2026-07-05T11:47:16.401671+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OWG5W7ZZSKD","created_at":"2026-07-05T11:47:16.401671+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OWG5W7ZZSKDDTNM","created_at":"2026-07-05T11:47:16.401671+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OWG5W7Z","created_at":"2026-07-05T11:47:16.401671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01698","citing_title":"Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4","json":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4.json","graph_json":"https://pith.science/api/pith-number/3OWG5W7ZZSKDDTNMNIN4KHO2E4/graph.json","events_json":"https://pith.science/api/pith-number/3OWG5W7ZZSKDDTNMNIN4KHO2E4/events.json","paper":"https://pith.science/paper/3OWG5W7Z"},"agent_actions":{"view_html":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4","download_json":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4.json","view_paper":"https://pith.science/paper/3OWG5W7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04887&json=true","fetch_graph":"https://pith.science/api/pith-number/3OWG5W7ZZSKDDTNMNIN4KHO2E4/graph.json","fetch_events":"https://pith.science/api/pith-number/3OWG5W7ZZSKDDTNMNIN4KHO2E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4/action/storage_attestation","attest_author":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4/action/author_attestation","sign_citation":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4/action/citation_signature","submit_replication":"https://pith.science/pith/3OWG5W7ZZSKDDTNMNIN4KHO2E4/action/replication_record"}},"created_at":"2026-07-05T11:47:16.401671+00:00","updated_at":"2026-07-05T11:47:16.401671+00:00"}