{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7DQJPVYA574DLWN4Z66USI7JTZ","short_pith_number":"pith:7DQJPVYA","schema_version":"1.0","canonical_sha256":"f8e097d700eff835d9bccfbd4923e99e7fa83509be36f04b1202ddfebefe31fe","source":{"kind":"arxiv","id":"2502.18959","version":3},"attestation_state":"computed","paper":{"title":"Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haomin Zhou, Hongkai Zhao, Shijun Zhang, Yimin Zhong","submitted_at":"2025-02-26T09:12:52Z","abstract_excerpt":"The architecture of a neural network and the choice of its activation function are both fundamental to its performance. Equally important is ensuring that these two elements are well matched, as their alignment is key to effective representation and learning. In this paper, we introduce the Fourier Multi-Component and Multi-Layer Neural Network (FMMNN), a model that combines sine-type activations with the multi-component and multi-layer structure of MMNNs. In an FMMNN, each component is represented as a trainable linear combination of fixed random sine-type basis functions, while multi-layer c"},"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":"2502.18959","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T09:12:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ece3ac6e504a28c6bd2494bedde1dc7b420556686a40c94d66592f931c87448c","abstract_canon_sha256":"4d9c23fe8e07700b43f2883d886e167dd4f8bc0900cc4c439094765202afd0be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:07.484206Z","signature_b64":"mPpIzQk6y/zlaUPJ/KrI91tvVcXIFtvpjo1kxjhGszVTzz6QXTgRzdoJXE9P6p6AlZawWaMhpl/p27KvhPpiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e097d700eff835d9bccfbd4923e99e7fa83509be36f04b1202ddfebefe31fe","last_reissued_at":"2026-06-12T01:09:07.483138Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:07.483138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haomin Zhou, Hongkai Zhao, Shijun Zhang, Yimin Zhong","submitted_at":"2025-02-26T09:12:52Z","abstract_excerpt":"The architecture of a neural network and the choice of its activation function are both fundamental to its performance. Equally important is ensuring that these two elements are well matched, as their alignment is key to effective representation and learning. In this paper, we introduce the Fourier Multi-Component and Multi-Layer Neural Network (FMMNN), a model that combines sine-type activations with the multi-component and multi-layer structure of MMNNs. In an FMMNN, each component is represented as a trainable linear combination of fixed random sine-type basis functions, while multi-layer c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18959","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/2502.18959/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":"2502.18959","created_at":"2026-06-12T01:09:07.483261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18959v3","created_at":"2026-06-12T01:09:07.483261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18959","created_at":"2026-06-12T01:09:07.483261+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DQJPVYA574D","created_at":"2026-06-12T01:09:07.483261+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DQJPVYA574DLWN4","created_at":"2026-06-12T01:09:07.483261+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DQJPVYA","created_at":"2026-06-12T01:09:07.483261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2602.17776","citing_title":"Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20219","citing_title":"Geometric Layer-wise Approximation Rates for Deep Networks","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ","json":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ.json","graph_json":"https://pith.science/api/pith-number/7DQJPVYA574DLWN4Z66USI7JTZ/graph.json","events_json":"https://pith.science/api/pith-number/7DQJPVYA574DLWN4Z66USI7JTZ/events.json","paper":"https://pith.science/paper/7DQJPVYA"},"agent_actions":{"view_html":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ","download_json":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ.json","view_paper":"https://pith.science/paper/7DQJPVYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18959&json=true","fetch_graph":"https://pith.science/api/pith-number/7DQJPVYA574DLWN4Z66USI7JTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7DQJPVYA574DLWN4Z66USI7JTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ/action/storage_attestation","attest_author":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ/action/author_attestation","sign_citation":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ/action/citation_signature","submit_replication":"https://pith.science/pith/7DQJPVYA574DLWN4Z66USI7JTZ/action/replication_record"}},"created_at":"2026-06-12T01:09:07.483261+00:00","updated_at":"2026-06-12T01:09:07.483261+00:00"}