{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OQFW73BXDU5TL7UVMX2SBJO3BG","short_pith_number":"pith:OQFW73BX","schema_version":"1.0","canonical_sha256":"740b6fec371d3b35fe9565f520a5db099e4bcd3f18094f27adbaadf52d6b0342","source":{"kind":"arxiv","id":"2505.03042","version":1},"attestation_state":"computed","paper":{"title":"A New Perspective To Understanding Multi-resolution Hash Encoding For Neural Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Steven Tin Sui Luo","submitted_at":"2025-05-05T21:53:09Z","abstract_excerpt":"Instant-NGP has been the state-of-the-art architecture of neural fields in recent years. Its incredible signal-fitting capabilities are generally attributed to its multi-resolution hash grid structure and have been used and improved in numerous following works. However, it is unclear how and why such a hash grid structure improves the capabilities of a neural network by such great margins. A lack of principled understanding of the hash grid also implies that the large set of hyperparameters accompanying Instant-NGP could only be tuned empirically without much heuristics. To provide an intuitiv"},"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":"2505.03042","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T21:53:09Z","cross_cats_sorted":[],"title_canon_sha256":"945880d070f5ce4a792158dc267f17cf86287db10b2191417f5ca30f769ab54c","abstract_canon_sha256":"3a291b64928ca6c101ff69267ce7ca7c21aec3c90d4bb9c43a1fc8de45b6242c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:51.735187Z","signature_b64":"9xi7fhkyOow3+DsGb8Ugnrz/VScaDuLsB4UapsyrjuPr7lJvtlq/+yAWkZkdxvBTqVl+knTYD16GlEEQ0Of7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"740b6fec371d3b35fe9565f520a5db099e4bcd3f18094f27adbaadf52d6b0342","last_reissued_at":"2026-07-05T10:58:51.734617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:51.734617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New Perspective To Understanding Multi-resolution Hash Encoding For Neural Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Steven Tin Sui Luo","submitted_at":"2025-05-05T21:53:09Z","abstract_excerpt":"Instant-NGP has been the state-of-the-art architecture of neural fields in recent years. Its incredible signal-fitting capabilities are generally attributed to its multi-resolution hash grid structure and have been used and improved in numerous following works. However, it is unclear how and why such a hash grid structure improves the capabilities of a neural network by such great margins. A lack of principled understanding of the hash grid also implies that the large set of hyperparameters accompanying Instant-NGP could only be tuned empirically without much heuristics. To provide an intuitiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03042","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/2505.03042/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":"2505.03042","created_at":"2026-07-05T10:58:51.734676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03042v1","created_at":"2026-07-05T10:58:51.734676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03042","created_at":"2026-07-05T10:58:51.734676+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQFW73BXDU5T","created_at":"2026-07-05T10:58:51.734676+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQFW73BXDU5TL7UV","created_at":"2026-07-05T10:58:51.734676+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQFW73BX","created_at":"2026-07-05T10:58:51.734676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.27825","citing_title":"Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG","json":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG.json","graph_json":"https://pith.science/api/pith-number/OQFW73BXDU5TL7UVMX2SBJO3BG/graph.json","events_json":"https://pith.science/api/pith-number/OQFW73BXDU5TL7UVMX2SBJO3BG/events.json","paper":"https://pith.science/paper/OQFW73BX"},"agent_actions":{"view_html":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG","download_json":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG.json","view_paper":"https://pith.science/paper/OQFW73BX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03042&json=true","fetch_graph":"https://pith.science/api/pith-number/OQFW73BXDU5TL7UVMX2SBJO3BG/graph.json","fetch_events":"https://pith.science/api/pith-number/OQFW73BXDU5TL7UVMX2SBJO3BG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG/action/storage_attestation","attest_author":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG/action/author_attestation","sign_citation":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG/action/citation_signature","submit_replication":"https://pith.science/pith/OQFW73BXDU5TL7UVMX2SBJO3BG/action/replication_record"}},"created_at":"2026-07-05T10:58:51.734676+00:00","updated_at":"2026-07-05T10:58:51.734676+00:00"}