{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3EUPPDWKMQYTYDYCQCE4VLOBBI","short_pith_number":"pith:3EUPPDWK","schema_version":"1.0","canonical_sha256":"d928f78eca64313c0f028089caadc10a07efed47eec0c0726ae64b41c3221bef","source":{"kind":"arxiv","id":"2106.12372","version":2},"attestation_state":"computed","paper":{"title":"Real-time Neural Radiance Caching for Path Tracing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GR","authors_text":"Alexander Keller, Fabrice Rousselle, Jan Nov\\'ak, Thomas M\\\"uller","submitted_at":"2021-06-23T13:09:58Z","abstract_excerpt":"We present a real-time neural radiance caching method for path-traced global illumination. Our system is designed to handle fully dynamic scenes, and makes no assumptions about the lighting, geometry, and materials. The data-driven nature of our approach sidesteps many difficulties of caching algorithms, such as locating, interpolating, and updating cache points. Since pretraining neural networks to handle novel, dynamic scenes is a formidable generalization challenge, we do away with pretraining and instead achieve generalization via adaptation, i.e. we opt for training the radiance cache whi"},"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":"2106.12372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2021-06-23T13:09:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"47790f69f04c6e41189430935b1c2a5e1076a2b6d9f7b5cc735ee3311f1098cd","abstract_canon_sha256":"bd61a518bd65e7c633d1a8fe9af77e55f55042795aac1cde58df7e96b8800b73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:17.119544Z","signature_b64":"W6SRMDvDSmOHAS29wa1tBAK3xv2QYsSY5je3BBeEAVNmM5ZGECOXXcdPrw+gIt4y9fohA4gwPil5KlxSZWxcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d928f78eca64313c0f028089caadc10a07efed47eec0c0726ae64b41c3221bef","last_reissued_at":"2026-07-05T02:52:17.119124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:17.119124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-time Neural Radiance Caching for Path Tracing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GR","authors_text":"Alexander Keller, Fabrice Rousselle, Jan Nov\\'ak, Thomas M\\\"uller","submitted_at":"2021-06-23T13:09:58Z","abstract_excerpt":"We present a real-time neural radiance caching method for path-traced global illumination. Our system is designed to handle fully dynamic scenes, and makes no assumptions about the lighting, geometry, and materials. The data-driven nature of our approach sidesteps many difficulties of caching algorithms, such as locating, interpolating, and updating cache points. Since pretraining neural networks to handle novel, dynamic scenes is a formidable generalization challenge, we do away with pretraining and instead achieve generalization via adaptation, i.e. we opt for training the radiance cache whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12372","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/2106.12372/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":"2106.12372","created_at":"2026-07-05T02:52:17.119187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.12372v2","created_at":"2026-07-05T02:52:17.119187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12372","created_at":"2026-07-05T02:52:17.119187+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EUPPDWKMQYT","created_at":"2026-07-05T02:52:17.119187+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EUPPDWKMQYTYDYC","created_at":"2026-07-05T02:52:17.119187+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EUPPDWK","created_at":"2026-07-05T02:52:17.119187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05907","citing_title":"Neural Field Representations of Mobile Computational Photography","ref_index":140,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI","json":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI.json","graph_json":"https://pith.science/api/pith-number/3EUPPDWKMQYTYDYCQCE4VLOBBI/graph.json","events_json":"https://pith.science/api/pith-number/3EUPPDWKMQYTYDYCQCE4VLOBBI/events.json","paper":"https://pith.science/paper/3EUPPDWK"},"agent_actions":{"view_html":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI","download_json":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI.json","view_paper":"https://pith.science/paper/3EUPPDWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.12372&json=true","fetch_graph":"https://pith.science/api/pith-number/3EUPPDWKMQYTYDYCQCE4VLOBBI/graph.json","fetch_events":"https://pith.science/api/pith-number/3EUPPDWKMQYTYDYCQCE4VLOBBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI/action/storage_attestation","attest_author":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI/action/author_attestation","sign_citation":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI/action/citation_signature","submit_replication":"https://pith.science/pith/3EUPPDWKMQYTYDYCQCE4VLOBBI/action/replication_record"}},"created_at":"2026-07-05T02:52:17.119187+00:00","updated_at":"2026-07-05T02:52:17.119187+00:00"}