{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LT5HK574FDYZSMHXQVCYXETJGV","short_pith_number":"pith:LT5HK574","schema_version":"1.0","canonical_sha256":"5cfa7577fc28f19930f785458b9269355993a19b7d461d566c05f47089c5768a","source":{"kind":"arxiv","id":"2507.13475","version":1},"attestation_state":"computed","paper":{"title":"Expansive Natural Neural Gradient Flows for Energy Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Wolfgang Dahmen, Wuchen Li, Yuankai Teng, Zhu Wang","submitted_at":"2025-07-17T18:35:11Z","abstract_excerpt":"This paper develops expansive gradient dynamics in deep neural network-induced mapping spaces. Specifically, we generate tools and concepts for minimizing a class of energy functionals in an abstract Hilbert space setting covering a wide scope of applications such as PDEs-based inverse problems and supervised learning. The approach hinges on a Hilbert space metric in the full diffeomorphism mapping space, which could be viewed as a generalized Wasserstein-2 metric. We then study a projection gradient descent method within deep neural network parameterized sets. More importantly, we develop an "},"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":"2507.13475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-07-17T18:35:11Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"04a701a3417a0a88e0bf0cc0d21b4b68453143ff4d3e4504dcb4b8a3f9e96f28","abstract_canon_sha256":"1e1142dc6b9e325d928dde12b6f6be603319f0f837a14d0b6686ff8d82f6420c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:18.020566Z","signature_b64":"yKfUnPG45OsU8Lm2AgxiDZFiYiIxcyq6fg7RU+eYysfGtxTNOXpf7KTvcXVodA2XTj9mnqVPUHgSpr2xOZwBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cfa7577fc28f19930f785458b9269355993a19b7d461d566c05f47089c5768a","last_reissued_at":"2026-07-05T11:39:18.020054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:18.020054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expansive Natural Neural Gradient Flows for Energy Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Wolfgang Dahmen, Wuchen Li, Yuankai Teng, Zhu Wang","submitted_at":"2025-07-17T18:35:11Z","abstract_excerpt":"This paper develops expansive gradient dynamics in deep neural network-induced mapping spaces. Specifically, we generate tools and concepts for minimizing a class of energy functionals in an abstract Hilbert space setting covering a wide scope of applications such as PDEs-based inverse problems and supervised learning. The approach hinges on a Hilbert space metric in the full diffeomorphism mapping space, which could be viewed as a generalized Wasserstein-2 metric. We then study a projection gradient descent method within deep neural network parameterized sets. More importantly, we develop an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13475","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/2507.13475/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":"2507.13475","created_at":"2026-07-05T11:39:18.020125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13475v1","created_at":"2026-07-05T11:39:18.020125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13475","created_at":"2026-07-05T11:39:18.020125+00:00"},{"alias_kind":"pith_short_12","alias_value":"LT5HK574FDYZ","created_at":"2026-07-05T11:39:18.020125+00:00"},{"alias_kind":"pith_short_16","alias_value":"LT5HK574FDYZSMHX","created_at":"2026-07-05T11:39:18.020125+00:00"},{"alias_kind":"pith_short_8","alias_value":"LT5HK574","created_at":"2026-07-05T11:39:18.020125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27779","citing_title":"Global Convergence and Error Propagation in Neural Gradient Flows: A Riemannian Optimization Framework","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00284","citing_title":"A Dirac-Frenkel-Onsager principle: Instantaneous residual minimization with gauge momentum for nonlinear parametrizations of PDE solutions","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV","json":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV.json","graph_json":"https://pith.science/api/pith-number/LT5HK574FDYZSMHXQVCYXETJGV/graph.json","events_json":"https://pith.science/api/pith-number/LT5HK574FDYZSMHXQVCYXETJGV/events.json","paper":"https://pith.science/paper/LT5HK574"},"agent_actions":{"view_html":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV","download_json":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV.json","view_paper":"https://pith.science/paper/LT5HK574","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13475&json=true","fetch_graph":"https://pith.science/api/pith-number/LT5HK574FDYZSMHXQVCYXETJGV/graph.json","fetch_events":"https://pith.science/api/pith-number/LT5HK574FDYZSMHXQVCYXETJGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV/action/storage_attestation","attest_author":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV/action/author_attestation","sign_citation":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV/action/citation_signature","submit_replication":"https://pith.science/pith/LT5HK574FDYZSMHXQVCYXETJGV/action/replication_record"}},"created_at":"2026-07-05T11:39:18.020125+00:00","updated_at":"2026-07-05T11:39:18.020125+00:00"}