{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5ZW7XOXUAFZ7OI7G2PIBATME4P","short_pith_number":"pith:5ZW7XOXU","schema_version":"1.0","canonical_sha256":"ee6dfbbaf40173f723e6d3d0104d84e3de7965102be1ada0390a1ee754bcd76a","source":{"kind":"arxiv","id":"2201.05989","version":2},"attestation_state":"computed","paper":{"title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Keller, Alex Evans, Christoph Schied, Thomas M\\\"uller","submitted_at":"2022-01-16T07:22:47Z","abstract_excerpt":"Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations: a small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architec"},"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":"2201.05989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-16T07:22:47Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"772a94dd060b68fa8ce43e71c1b16ecf8b991f417c724ffb13cf1188a9776d7d","abstract_canon_sha256":"ffbc6fa4790ec28db03029f233c1932ad124f6354c5ddc6f8f649ce356de96cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:18.101499Z","signature_b64":"qP9XEW7p7wpydX6BUYMiOnhhPRQoSTyid1jL2QqkGMoZN7W4+WdID43wo0jOBX3KeoSZZVrQktLwzphth5fgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee6dfbbaf40173f723e6d3d0104d84e3de7965102be1ada0390a1ee754bcd76a","last_reissued_at":"2026-07-05T04:20:18.101020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:18.101020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Keller, Alex Evans, Christoph Schied, Thomas M\\\"uller","submitted_at":"2022-01-16T07:22:47Z","abstract_excerpt":"Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations: a small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05989","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/2201.05989/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":"2201.05989","created_at":"2026-07-05T04:20:18.101077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05989v2","created_at":"2026-07-05T04:20:18.101077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05989","created_at":"2026-07-05T04:20:18.101077+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZW7XOXUAFZ7","created_at":"2026-07-05T04:20:18.101077+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZW7XOXUAFZ7OI7G","created_at":"2026-07-05T04:20:18.101077+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZW7XOXU","created_at":"2026-07-05T04:20:18.101077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20272","citing_title":"Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18156","citing_title":"ReAge3D: Re-Aging 3D Faces with View Consistency","ref_index":188,"is_internal_anchor":false},{"citing_arxiv_id":"2205.13524","citing_title":"PREF: Phasorial Embedding Fields for Compact Neural Representations","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09299","citing_title":"LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P","json":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P.json","graph_json":"https://pith.science/api/pith-number/5ZW7XOXUAFZ7OI7G2PIBATME4P/graph.json","events_json":"https://pith.science/api/pith-number/5ZW7XOXUAFZ7OI7G2PIBATME4P/events.json","paper":"https://pith.science/paper/5ZW7XOXU"},"agent_actions":{"view_html":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P","download_json":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P.json","view_paper":"https://pith.science/paper/5ZW7XOXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05989&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZW7XOXUAFZ7OI7G2PIBATME4P/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZW7XOXUAFZ7OI7G2PIBATME4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P/action/storage_attestation","attest_author":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P/action/author_attestation","sign_citation":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P/action/citation_signature","submit_replication":"https://pith.science/pith/5ZW7XOXUAFZ7OI7G2PIBATME4P/action/replication_record"}},"created_at":"2026-07-05T04:20:18.101077+00:00","updated_at":"2026-07-05T04:20:18.101077+00:00"}