{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4ZJGR6IKN3ZUAZKOVZ62YB3CAG","short_pith_number":"pith:4ZJGR6IK","schema_version":"1.0","canonical_sha256":"e65268f90a6ef340654eae7dac0762019cf31be136dbcce06d17769af67445df","source":{"kind":"arxiv","id":"2308.14737","version":1},"attestation_state":"computed","paper":{"title":"Flexible Techniques for Differentiable Rendering with 3D Gaussians","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Leonid Keselman, Martial Hebert","submitted_at":"2023-08-28T17:38:31Z","abstract_excerpt":"Fast, reliable shape reconstruction is an essential ingredient in many computer vision applications. Neural Radiance Fields demonstrated that photorealistic novel view synthesis is within reach, but was gated by performance requirements for fast reconstruction of real scenes and objects. Several recent approaches have built on alternative shape representations, in particular, 3D Gaussians. We develop extensions to these renderers, such as integrating differentiable optical flow, exporting watertight meshes and rendering per-ray normals. Additionally, we show how two of the recent methods are i"},"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":"2308.14737","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T17:38:31Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"9cee946e0a248e256762b1053b90f64b50b3afa41c19b04c52254ea6d78e6d46","abstract_canon_sha256":"d4cb7fedbc8045c6fd0f6787384619d7bd20ed5c87049fef753a53fb39136492"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:30.449408Z","signature_b64":"IH0wmQakIvtIP8svDsKxhGe4KMn5rGa6eA0Jbf6wfskLwidcr1643sp5UWEn0O43Sbz1fhY6hMnScDJcv9ynCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e65268f90a6ef340654eae7dac0762019cf31be136dbcce06d17769af67445df","last_reissued_at":"2026-07-05T06:45:30.448878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:30.448878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flexible Techniques for Differentiable Rendering with 3D Gaussians","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Leonid Keselman, Martial Hebert","submitted_at":"2023-08-28T17:38:31Z","abstract_excerpt":"Fast, reliable shape reconstruction is an essential ingredient in many computer vision applications. Neural Radiance Fields demonstrated that photorealistic novel view synthesis is within reach, but was gated by performance requirements for fast reconstruction of real scenes and objects. Several recent approaches have built on alternative shape representations, in particular, 3D Gaussians. We develop extensions to these renderers, such as integrating differentiable optical flow, exporting watertight meshes and rendering per-ray normals. Additionally, we show how two of the recent methods are i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14737","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/2308.14737/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":"2308.14737","created_at":"2026-07-05T06:45:30.448939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14737v1","created_at":"2026-07-05T06:45:30.448939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14737","created_at":"2026-07-05T06:45:30.448939+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZJGR6IKN3ZU","created_at":"2026-07-05T06:45:30.448939+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZJGR6IKN3ZUAZKO","created_at":"2026-07-05T06:45:30.448939+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZJGR6IK","created_at":"2026-07-05T06:45:30.448939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02096","citing_title":"WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG","json":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG.json","graph_json":"https://pith.science/api/pith-number/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/graph.json","events_json":"https://pith.science/api/pith-number/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/events.json","paper":"https://pith.science/paper/4ZJGR6IK"},"agent_actions":{"view_html":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG","download_json":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG.json","view_paper":"https://pith.science/paper/4ZJGR6IK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14737&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/action/storage_attestation","attest_author":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/action/author_attestation","sign_citation":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/action/citation_signature","submit_replication":"https://pith.science/pith/4ZJGR6IKN3ZUAZKOVZ62YB3CAG/action/replication_record"}},"created_at":"2026-07-05T06:45:30.448939+00:00","updated_at":"2026-07-05T06:45:30.448939+00:00"}