{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TOAZCKMD43ETAN7W62U5OVZAIA","short_pith_number":"pith:TOAZCKMD","schema_version":"1.0","canonical_sha256":"9b81912983e6c93037f6f6a9d757204022af455f2c74abbe3839d8acaf929cd6","source":{"kind":"arxiv","id":"2404.09591","version":3},"attestation_state":"computed","paper":{"title":"3D Gaussian Splatting as Markov Chain Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Kar, Andrea Tagliasacchi, Daniel Rebain, Gopal Sharma, Hossam Isack, Jeff Tseng, Kwang Moo Yi, Shakiba Kheradmand, Weiwei Sun","submitted_at":"2024-04-15T09:01:47Z","abstract_excerpt":"While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, which can lead to poor-quality renderings, and reliance on a good initialization. In this work, we rethink the set of 3D Gaussians as a random sample drawn from an underlying probability distribution describing the physical representation of the scene-in other words, Markov Chain Monte Carlo (MCMC) samples. Under this view, we show that the 3D Gaussian updates can be converted as Stochastic Gradient Langevin Dynamics "},"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":"2404.09591","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T09:01:47Z","cross_cats_sorted":[],"title_canon_sha256":"5436e081abea2e299a79668a89450a9877b3241de0afa4a399dd9d6f98b92d0f","abstract_canon_sha256":"6e11ed15da3e85fb761e8e131d192dc1515862a6506c49f7cbe1209fe9df4cb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:59.784472Z","signature_b64":"wP6fV0EYV8HSJDJ4V2rEU41IGt8/ntU2yRU6jaeoTATO2t4mwQDlDPtwuaK+XH33drnM1xpnTIDttUC40ZlMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b81912983e6c93037f6f6a9d757204022af455f2c74abbe3839d8acaf929cd6","last_reissued_at":"2026-07-05T10:12:59.783992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:59.783992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Gaussian Splatting as Markov Chain Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Kar, Andrea Tagliasacchi, Daniel Rebain, Gopal Sharma, Hossam Isack, Jeff Tseng, Kwang Moo Yi, Shakiba Kheradmand, Weiwei Sun","submitted_at":"2024-04-15T09:01:47Z","abstract_excerpt":"While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, which can lead to poor-quality renderings, and reliance on a good initialization. In this work, we rethink the set of 3D Gaussians as a random sample drawn from an underlying probability distribution describing the physical representation of the scene-in other words, Markov Chain Monte Carlo (MCMC) samples. Under this view, we show that the 3D Gaussian updates can be converted as Stochastic Gradient Langevin Dynamics "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09591","kind":"arxiv","version":3},"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/2404.09591/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":"2404.09591","created_at":"2026-07-05T10:12:59.784051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09591v3","created_at":"2026-07-05T10:12:59.784051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09591","created_at":"2026-07-05T10:12:59.784051+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOAZCKMD43ET","created_at":"2026-07-05T10:12:59.784051+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOAZCKMD43ETAN7W","created_at":"2026-07-05T10:12:59.784051+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOAZCKMD","created_at":"2026-07-05T10:12:59.784051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30017","citing_title":"Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03077","citing_title":"RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13547","citing_title":"Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA","json":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA.json","graph_json":"https://pith.science/api/pith-number/TOAZCKMD43ETAN7W62U5OVZAIA/graph.json","events_json":"https://pith.science/api/pith-number/TOAZCKMD43ETAN7W62U5OVZAIA/events.json","paper":"https://pith.science/paper/TOAZCKMD"},"agent_actions":{"view_html":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA","download_json":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA.json","view_paper":"https://pith.science/paper/TOAZCKMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09591&json=true","fetch_graph":"https://pith.science/api/pith-number/TOAZCKMD43ETAN7W62U5OVZAIA/graph.json","fetch_events":"https://pith.science/api/pith-number/TOAZCKMD43ETAN7W62U5OVZAIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA/action/storage_attestation","attest_author":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA/action/author_attestation","sign_citation":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA/action/citation_signature","submit_replication":"https://pith.science/pith/TOAZCKMD43ETAN7W62U5OVZAIA/action/replication_record"}},"created_at":"2026-07-05T10:12:59.784051+00:00","updated_at":"2026-07-05T10:12:59.784051+00:00"}