{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P4UY5W6XB2BRYAKKRNHVGGHQBS","short_pith_number":"pith:P4UY5W6X","schema_version":"1.0","canonical_sha256":"7f298edbd70e831c014a8b4f5318f00cb6591e24b86da702aa9b59eeb253b99d","source":{"kind":"arxiv","id":"2601.14821","version":1},"attestation_state":"computed","paper":{"title":"POTR: Post-Training 3DGS Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bert Ramlot, Glenn Van Wallendael, Martijn Courteaux, Peter Lambert","submitted_at":"2026-01-21T09:47:45Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has recently emerged as a promising contender to Neural Radiance Fields (NeRF) in 3D scene reconstruction and real-time novel view synthesis. 3DGS outperforms NeRF in training and inference speed but has substantially higher storage requirements. To remedy this downside, we propose POTR, a post-training 3DGS codec built on two novel techniques. First, POTR introduces a novel pruning approach that uses a modified 3DGS rasterizer to efficiently calculate every splat's individual removal effect simultaneously. This technique results in 2-4x fewer splats than other pos"},"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":"2601.14821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-21T09:47:45Z","cross_cats_sorted":[],"title_canon_sha256":"063823fe925b38ad61c5dd7f0b3ee67fc339b610afb068e4b277f1e1ba0cd0bf","abstract_canon_sha256":"b1330e74a62bf29d0529d2777bfe218be9dff46f94579afdc2402e6962c6dae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:12.304354Z","signature_b64":"cwWkoFYY54y+Cu5wLhLfxK0HFI1g0s3CO9Rnbctn/idSisTCI0eAxHwvTGEMkO2B068FlDIjIHATCpu1hFLLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f298edbd70e831c014a8b4f5318f00cb6591e24b86da702aa9b59eeb253b99d","last_reissued_at":"2026-05-25T02:01:12.303625Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:12.303625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POTR: Post-Training 3DGS Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bert Ramlot, Glenn Van Wallendael, Martijn Courteaux, Peter Lambert","submitted_at":"2026-01-21T09:47:45Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has recently emerged as a promising contender to Neural Radiance Fields (NeRF) in 3D scene reconstruction and real-time novel view synthesis. 3DGS outperforms NeRF in training and inference speed but has substantially higher storage requirements. To remedy this downside, we propose POTR, a post-training 3DGS codec built on two novel techniques. First, POTR introduces a novel pruning approach that uses a modified 3DGS rasterizer to efficiently calculate every splat's individual removal effect simultaneously. This technique results in 2-4x fewer splats than other pos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14821","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/2601.14821/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":"2601.14821","created_at":"2026-05-25T02:01:12.303737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.14821v1","created_at":"2026-05-25T02:01:12.303737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14821","created_at":"2026-05-25T02:01:12.303737+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4UY5W6XB2BR","created_at":"2026-05-25T02:01:12.303737+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4UY5W6XB2BRYAKK","created_at":"2026-05-25T02:01:12.303737+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4UY5W6X","created_at":"2026-05-25T02:01:12.303737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.26799","citing_title":"MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26799","citing_title":"MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS","json":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS.json","graph_json":"https://pith.science/api/pith-number/P4UY5W6XB2BRYAKKRNHVGGHQBS/graph.json","events_json":"https://pith.science/api/pith-number/P4UY5W6XB2BRYAKKRNHVGGHQBS/events.json","paper":"https://pith.science/paper/P4UY5W6X"},"agent_actions":{"view_html":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS","download_json":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS.json","view_paper":"https://pith.science/paper/P4UY5W6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.14821&json=true","fetch_graph":"https://pith.science/api/pith-number/P4UY5W6XB2BRYAKKRNHVGGHQBS/graph.json","fetch_events":"https://pith.science/api/pith-number/P4UY5W6XB2BRYAKKRNHVGGHQBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS/action/storage_attestation","attest_author":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS/action/author_attestation","sign_citation":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS/action/citation_signature","submit_replication":"https://pith.science/pith/P4UY5W6XB2BRYAKKRNHVGGHQBS/action/replication_record"}},"created_at":"2026-05-25T02:01:12.303737+00:00","updated_at":"2026-05-25T02:01:12.303737+00:00"}