{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NQTYTVFUTJYMI57GZCGXKQ6HQZ","short_pith_number":"pith:NQTYTVFU","schema_version":"1.0","canonical_sha256":"6c2789d4b49a70c477e6c88d7543c7865535d8d820d97bd09ad02f7b04984faa","source":{"kind":"arxiv","id":"2508.15198","version":2},"attestation_state":"computed","paper":{"title":"Frequency-adaptive tensor neural networks for high-dimensional multi-scale problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math-ph","math.MP"],"primary_cat":"cs.LG","authors_text":"Jizu Huang, Rukang You, Yue Qiu","submitted_at":"2025-08-21T03:16:52Z","abstract_excerpt":"Tensor neural networks (TNNs) have demonstrated their superiority in solving high-dimensional problems. However, similar to conventional neural networks, TNNs are also influenced by the Frequency Principle, which limits their ability to accurately capture high-frequency features of the solution. In this work, we analyze the training dynamics of TNNs by Fourier analysis and enhance their expressivity for high-dimensional multi-scale problems by incorporating random Fourier features. Leveraging the inherent tensor structure of TNNs, we further propose a novel approach to extract frequency featur"},"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":"2508.15198","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-21T03:16:52Z","cross_cats_sorted":["math-ph","math.MP"],"title_canon_sha256":"6e7af92611fd7c6c3fe6badd7bf45d304681c3de7e6c9852ea2b793c5e553cfa","abstract_canon_sha256":"19b899b989c7ba5e92081e6a46b553ae6e7e588aeb78e62b9960e4acf0574bc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:04.809374Z","signature_b64":"QZH/5sTaxBf314r3bSI28MlABmtViUQFxYeJmrubUfFQAma36/B0xzbthoXPDRb4ubc1/oow5mWSjZV/QdtfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c2789d4b49a70c477e6c88d7543c7865535d8d820d97bd09ad02f7b04984faa","last_reissued_at":"2026-05-17T23:39:04.808773Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:04.808773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frequency-adaptive tensor neural networks for high-dimensional multi-scale problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math-ph","math.MP"],"primary_cat":"cs.LG","authors_text":"Jizu Huang, Rukang You, Yue Qiu","submitted_at":"2025-08-21T03:16:52Z","abstract_excerpt":"Tensor neural networks (TNNs) have demonstrated their superiority in solving high-dimensional problems. However, similar to conventional neural networks, TNNs are also influenced by the Frequency Principle, which limits their ability to accurately capture high-frequency features of the solution. In this work, we analyze the training dynamics of TNNs by Fourier analysis and enhance their expressivity for high-dimensional multi-scale problems by incorporating random Fourier features. Leveraging the inherent tensor structure of TNNs, we further propose a novel approach to extract frequency featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15198","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":""},"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":"2508.15198","created_at":"2026-05-17T23:39:04.808886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15198v2","created_at":"2026-05-17T23:39:04.808886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15198","created_at":"2026-05-17T23:39:04.808886+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQTYTVFUTJYM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQTYTVFUTJYMI57G","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQTYTVFU","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ","json":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ.json","graph_json":"https://pith.science/api/pith-number/NQTYTVFUTJYMI57GZCGXKQ6HQZ/graph.json","events_json":"https://pith.science/api/pith-number/NQTYTVFUTJYMI57GZCGXKQ6HQZ/events.json","paper":"https://pith.science/paper/NQTYTVFU"},"agent_actions":{"view_html":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ","download_json":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ.json","view_paper":"https://pith.science/paper/NQTYTVFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15198&json=true","fetch_graph":"https://pith.science/api/pith-number/NQTYTVFUTJYMI57GZCGXKQ6HQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NQTYTVFUTJYMI57GZCGXKQ6HQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ/action/storage_attestation","attest_author":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ/action/author_attestation","sign_citation":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ/action/citation_signature","submit_replication":"https://pith.science/pith/NQTYTVFUTJYMI57GZCGXKQ6HQZ/action/replication_record"}},"created_at":"2026-05-17T23:39:04.808886+00:00","updated_at":"2026-05-17T23:39:04.808886+00:00"}