{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FSXRBUYL7TBUC6YO6UJZKDPSGQ","short_pith_number":"pith:FSXRBUYL","schema_version":"1.0","canonical_sha256":"2caf10d30bfcc3417b0ef513950df234006db2ca288f6c298304aa5d67160d4d","source":{"kind":"arxiv","id":"2512.14366","version":2},"attestation_state":"computed","paper":{"title":"Optimizing Rank for High-Fidelity Implicit Neural Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benedikt Wiestler, Bj\\\"orn Menze, Daniel Rueckert, Florentin Bieder, Florian A. H\\\"olzl, Julian McGinnis, Mark M\\\"uhlau, Paul Friedrich, Suprosanna Shit","submitted_at":"2025-12-16T12:52:30Z","abstract_excerpt":"Implicit Neural Representations (INRs) based on vanilla Multi-Layer Perceptrons (MLPs) are widely believed to be incapable of representing high-frequency content. This has directed research efforts towards architectural interventions, such as coordinate embeddings or specialized activation functions, to represent high-frequency signals. In this paper, we challenge the notion that the low-frequency bias of vanilla MLPs is an intrinsic, architectural limitation to learn high-frequency content, but instead a symptom of stable rank degradation during training. We empirically demonstrate that regul"},"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":"2512.14366","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-16T12:52:30Z","cross_cats_sorted":[],"title_canon_sha256":"a74166bd0e9f30ba15b34a4c6fe043086290923f8e7c0b391b2f052166ee0c17","abstract_canon_sha256":"7c06b19a992013f7beca49828905a34ac7618ab19621954ed8a3ba6ef6987084"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:27.291169Z","signature_b64":"giG2uZvVe26TSOrbZMqMict7VkDaAiGmdADzAgA52J572TGlH4hhMRLZICayzksy14Y1q4szgnr/wgs/yRQCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2caf10d30bfcc3417b0ef513950df234006db2ca288f6c298304aa5d67160d4d","last_reissued_at":"2026-06-01T01:02:27.290167Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:27.290167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Rank for High-Fidelity Implicit Neural Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benedikt Wiestler, Bj\\\"orn Menze, Daniel Rueckert, Florentin Bieder, Florian A. H\\\"olzl, Julian McGinnis, Mark M\\\"uhlau, Paul Friedrich, Suprosanna Shit","submitted_at":"2025-12-16T12:52:30Z","abstract_excerpt":"Implicit Neural Representations (INRs) based on vanilla Multi-Layer Perceptrons (MLPs) are widely believed to be incapable of representing high-frequency content. This has directed research efforts towards architectural interventions, such as coordinate embeddings or specialized activation functions, to represent high-frequency signals. In this paper, we challenge the notion that the low-frequency bias of vanilla MLPs is an intrinsic, architectural limitation to learn high-frequency content, but instead a symptom of stable rank degradation during training. We empirically demonstrate that regul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.14366","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/2512.14366/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":"2512.14366","created_at":"2026-06-01T01:02:27.290309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.14366v2","created_at":"2026-06-01T01:02:27.290309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14366","created_at":"2026-06-01T01:02:27.290309+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSXRBUYL7TBU","created_at":"2026-06-01T01:02:27.290309+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSXRBUYL7TBUC6YO","created_at":"2026-06-01T01:02:27.290309+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSXRBUYL","created_at":"2026-06-01T01:02:27.290309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.08298","citing_title":"What Cohort INRs Encode and Where to Freeze Them","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15297","citing_title":"Benchmarking Optimizers for MLPs in Tabular Deep Learning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16800","citing_title":"Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoising","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ","json":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ.json","graph_json":"https://pith.science/api/pith-number/FSXRBUYL7TBUC6YO6UJZKDPSGQ/graph.json","events_json":"https://pith.science/api/pith-number/FSXRBUYL7TBUC6YO6UJZKDPSGQ/events.json","paper":"https://pith.science/paper/FSXRBUYL"},"agent_actions":{"view_html":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ","download_json":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ.json","view_paper":"https://pith.science/paper/FSXRBUYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.14366&json=true","fetch_graph":"https://pith.science/api/pith-number/FSXRBUYL7TBUC6YO6UJZKDPSGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FSXRBUYL7TBUC6YO6UJZKDPSGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ/action/storage_attestation","attest_author":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ/action/author_attestation","sign_citation":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ/action/citation_signature","submit_replication":"https://pith.science/pith/FSXRBUYL7TBUC6YO6UJZKDPSGQ/action/replication_record"}},"created_at":"2026-06-01T01:02:27.290309+00:00","updated_at":"2026-06-01T01:02:27.290309+00:00"}