{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HJRP3WRDHHXC3YQMAHROKY6MOG","short_pith_number":"pith:HJRP3WRD","schema_version":"1.0","canonical_sha256":"3a62fdda2339ee2de20c01e2e563cc718ee9a18e3c801d0c1e93f421475fe02a","source":{"kind":"arxiv","id":"2407.21121","version":3},"attestation_state":"computed","paper":{"title":"Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andre Araujo, Diana Aldana, Luiz Velho, Tiago Novello","submitted_at":"2024-07-30T18:24:46Z","abstract_excerpt":"Sinusoidal neural networks have been shown effective as implicit neural representations (INRs) of low-dimensional signals, due to their smoothness and high representation capacity. However, initializing and training them remain empirical tasks which lack on deeper understanding to guide the learning process. To fill this gap, our work introduces a theoretical framework that explains the capacity property of sinusoidal networks and offers robust control mechanisms for initialization and training. Our analysis is based on a novel amplitude-phase expansion of the sinusoidal multilayer perceptron,"},"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":"2407.21121","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-30T18:24:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e0ad4ef3ea327746e5ac8d13c6bb692a1736ffe1b0d71568bcc3164d0d3c6620","abstract_canon_sha256":"ea9e8cba30c5b86b342585bb0d24918f7e6e19086bde40ff63f713d0ff487348"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:15.417546Z","signature_b64":"jLcSK0f924/6kM//yHP3Y9LT9ow7m3vEfqZDl/MZesWHBris+66RZ4E3wXsqcRpMbW4Q9w8jXncVFRcDDLBcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a62fdda2339ee2de20c01e2e563cc718ee9a18e3c801d0c1e93f421475fe02a","last_reissued_at":"2026-07-05T10:44:15.417025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:15.417025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andre Araujo, Diana Aldana, Luiz Velho, Tiago Novello","submitted_at":"2024-07-30T18:24:46Z","abstract_excerpt":"Sinusoidal neural networks have been shown effective as implicit neural representations (INRs) of low-dimensional signals, due to their smoothness and high representation capacity. However, initializing and training them remain empirical tasks which lack on deeper understanding to guide the learning process. To fill this gap, our work introduces a theoretical framework that explains the capacity property of sinusoidal networks and offers robust control mechanisms for initialization and training. Our analysis is based on a novel amplitude-phase expansion of the sinusoidal multilayer perceptron,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21121","kind":"arxiv","version":3},"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/2407.21121/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":"2407.21121","created_at":"2026-07-05T10:44:15.417085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21121v3","created_at":"2026-07-05T10:44:15.417085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21121","created_at":"2026-07-05T10:44:15.417085+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJRP3WRDHHXC","created_at":"2026-07-05T10:44:15.417085+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJRP3WRDHHXC3YQM","created_at":"2026-07-05T10:44:15.417085+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJRP3WRD","created_at":"2026-07-05T10:44:15.417085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22556","citing_title":"ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":273,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG","json":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG.json","graph_json":"https://pith.science/api/pith-number/HJRP3WRDHHXC3YQMAHROKY6MOG/graph.json","events_json":"https://pith.science/api/pith-number/HJRP3WRDHHXC3YQMAHROKY6MOG/events.json","paper":"https://pith.science/paper/HJRP3WRD"},"agent_actions":{"view_html":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG","download_json":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG.json","view_paper":"https://pith.science/paper/HJRP3WRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21121&json=true","fetch_graph":"https://pith.science/api/pith-number/HJRP3WRDHHXC3YQMAHROKY6MOG/graph.json","fetch_events":"https://pith.science/api/pith-number/HJRP3WRDHHXC3YQMAHROKY6MOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG/action/storage_attestation","attest_author":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG/action/author_attestation","sign_citation":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG/action/citation_signature","submit_replication":"https://pith.science/pith/HJRP3WRDHHXC3YQMAHROKY6MOG/action/replication_record"}},"created_at":"2026-07-05T10:44:15.417085+00:00","updated_at":"2026-07-05T10:44:15.417085+00:00"}