{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WLAZJR2K5XEMFRUOE2GSYZYFO2","short_pith_number":"pith:WLAZJR2K","schema_version":"1.0","canonical_sha256":"b2c194c74aedc8c2c68e268d2c670576ad7d26a1151b924b960716d399acffda","source":{"kind":"arxiv","id":"2506.10973","version":1},"attestation_state":"computed","paper":{"title":"Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.FA","math.NA"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Boris Bonev, Jean Kossaifi, Julius Berner, Kamyar Azizzadenesheli, Miguel Liu-Schiaffini, Valentin Duruisseaux","submitted_at":"2025-06-12T17:59:31Z","abstract_excerpt":"A wide range of scientific problems, such as those described by continuous-time dynamical systems and partial differential equations (PDEs), are naturally formulated on function spaces. While function spaces are typically infinite-dimensional, deep learning has predominantly advanced through applications in computer vision and natural language processing that focus on mappings between finite-dimensional spaces. Such fundamental disparities in the nature of the data have limited neural networks from achieving a comparable level of success in scientific applications as seen in other fields. Neur"},"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":"2506.10973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:59:31Z","cross_cats_sorted":["cs.AI","cs.NA","math.FA","math.NA"],"title_canon_sha256":"6f77b0818372d2d7482c08ad3fdf68242d41631cffe36d4da7e4f94ceee521c6","abstract_canon_sha256":"2a75a590395baf690ce541638c451b78e28dacf216668177b6127dc561e6bf72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:41.328311Z","signature_b64":"C4OoOxa4Eo1AvrP9p6Y5njwhNVCZV2aUt79cpDENfe8WpDeRAwG7XuB77Oz+WQl6cWsJuy0V/a95cYVslbrsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2c194c74aedc8c2c68e268d2c670576ad7d26a1151b924b960716d399acffda","last_reissued_at":"2026-07-05T11:20:41.327770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:41.327770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.FA","math.NA"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Boris Bonev, Jean Kossaifi, Julius Berner, Kamyar Azizzadenesheli, Miguel Liu-Schiaffini, Valentin Duruisseaux","submitted_at":"2025-06-12T17:59:31Z","abstract_excerpt":"A wide range of scientific problems, such as those described by continuous-time dynamical systems and partial differential equations (PDEs), are naturally formulated on function spaces. While function spaces are typically infinite-dimensional, deep learning has predominantly advanced through applications in computer vision and natural language processing that focus on mappings between finite-dimensional spaces. Such fundamental disparities in the nature of the data have limited neural networks from achieving a comparable level of success in scientific applications as seen in other fields. Neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10973","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/2506.10973/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":"2506.10973","created_at":"2026-07-05T11:20:41.327845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10973v1","created_at":"2026-07-05T11:20:41.327845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10973","created_at":"2026-07-05T11:20:41.327845+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLAZJR2K5XEM","created_at":"2026-07-05T11:20:41.327845+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLAZJR2K5XEMFRUO","created_at":"2026-07-05T11:20:41.327845+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLAZJR2K","created_at":"2026-07-05T11:20:41.327845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08711","citing_title":"Evaluating Operators for Acoustic Wave Simulation Correction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28122","citing_title":"Higher-Order Fourier Neural Operator: Explicit Mode Mixer for Nonlinear PDEs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00677","citing_title":"Limits of Resolution Equivariance in Fourier Neural Operators","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25985","citing_title":"Learning Neural Operator Surrogates for the Black Hole Accretion Code","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2","json":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2.json","graph_json":"https://pith.science/api/pith-number/WLAZJR2K5XEMFRUOE2GSYZYFO2/graph.json","events_json":"https://pith.science/api/pith-number/WLAZJR2K5XEMFRUOE2GSYZYFO2/events.json","paper":"https://pith.science/paper/WLAZJR2K"},"agent_actions":{"view_html":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2","download_json":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2.json","view_paper":"https://pith.science/paper/WLAZJR2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10973&json=true","fetch_graph":"https://pith.science/api/pith-number/WLAZJR2K5XEMFRUOE2GSYZYFO2/graph.json","fetch_events":"https://pith.science/api/pith-number/WLAZJR2K5XEMFRUOE2GSYZYFO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2/action/storage_attestation","attest_author":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2/action/author_attestation","sign_citation":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2/action/citation_signature","submit_replication":"https://pith.science/pith/WLAZJR2K5XEMFRUOE2GSYZYFO2/action/replication_record"}},"created_at":"2026-07-05T11:20:41.327845+00:00","updated_at":"2026-07-05T11:20:41.327845+00:00"}