{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U2DNSC33AXKATWDFNFF22M5FFQ","short_pith_number":"pith:U2DNSC33","schema_version":"1.0","canonical_sha256":"a686d90b7b05d409d865694bad33a52c39b70a397471798efb32f5b0ce9d4838","source":{"kind":"arxiv","id":"2504.13412","version":1},"attestation_state":"computed","paper":{"title":"How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Matthias Zwicker, Samuel Audia, Soheil Feizi","submitted_at":"2025-04-18T02:18:08Z","abstract_excerpt":"Neural networks that map between low dimensional spaces are ubiquitous in computer graphics and scientific computing; however, in their naive implementation, they are unable to learn high frequency information. We present a comprehensive analysis comparing the two most common techniques for mitigating this spectral bias: Fourier feature encodings (FFE) and multigrid parametric encodings (MPE). FFEs are seen as the standard for low dimensional mappings, but MPEs often outperform them and learn representations with higher resolution and finer detail. FFE's roots in the Fourier transform, make it"},"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":"2504.13412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T02:18:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4f158c2c484c40ab832e113d09dd719bcbe4352584143429a19bc3ead7f107df","abstract_canon_sha256":"9c1fce616f6171022021f18eeaea6d4477ab8755b23f0e1d69619fa68acabe15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:54.517644Z","signature_b64":"NO2CT7Y87ch6aK3Ro76ARLNcqKNBHCKnsPLg3cX/0IUkANbznpATBT+vqqrn7NCWdMVA3FhNB/K4ominZa+mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a686d90b7b05d409d865694bad33a52c39b70a397471798efb32f5b0ce9d4838","last_reissued_at":"2026-07-05T10:50:54.517134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:54.517134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Matthias Zwicker, Samuel Audia, Soheil Feizi","submitted_at":"2025-04-18T02:18:08Z","abstract_excerpt":"Neural networks that map between low dimensional spaces are ubiquitous in computer graphics and scientific computing; however, in their naive implementation, they are unable to learn high frequency information. We present a comprehensive analysis comparing the two most common techniques for mitigating this spectral bias: Fourier feature encodings (FFE) and multigrid parametric encodings (MPE). FFEs are seen as the standard for low dimensional mappings, but MPEs often outperform them and learn representations with higher resolution and finer detail. FFE's roots in the Fourier transform, make it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13412","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/2504.13412/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":"2504.13412","created_at":"2026-07-05T10:50:54.517191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13412v1","created_at":"2026-07-05T10:50:54.517191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13412","created_at":"2026-07-05T10:50:54.517191+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2DNSC33AXKA","created_at":"2026-07-05T10:50:54.517191+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2DNSC33AXKATWDF","created_at":"2026-07-05T10:50:54.517191+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2DNSC33","created_at":"2026-07-05T10:50:54.517191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14370","citing_title":"Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel","ref_index":142,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ","json":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ.json","graph_json":"https://pith.science/api/pith-number/U2DNSC33AXKATWDFNFF22M5FFQ/graph.json","events_json":"https://pith.science/api/pith-number/U2DNSC33AXKATWDFNFF22M5FFQ/events.json","paper":"https://pith.science/paper/U2DNSC33"},"agent_actions":{"view_html":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ","download_json":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ.json","view_paper":"https://pith.science/paper/U2DNSC33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13412&json=true","fetch_graph":"https://pith.science/api/pith-number/U2DNSC33AXKATWDFNFF22M5FFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/U2DNSC33AXKATWDFNFF22M5FFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ/action/storage_attestation","attest_author":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ/action/author_attestation","sign_citation":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ/action/citation_signature","submit_replication":"https://pith.science/pith/U2DNSC33AXKATWDFNFF22M5FFQ/action/replication_record"}},"created_at":"2026-07-05T10:50:54.517191+00:00","updated_at":"2026-07-05T10:50:54.517191+00:00"}