{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TYPLYCY3CQZM6D25J56AE2GMQD","short_pith_number":"pith:TYPLYCY3","schema_version":"1.0","canonical_sha256":"9e1ebc0b1b1432cf0f5d4f7c0268cc80f69b5b1726e1c13a53a6e6b69c68ecbc","source":{"kind":"arxiv","id":"2111.13587","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Anima Anandkumar, Bryan Catanzaro, John Guibas, Morteza Mardani, Zongyi Li","submitted_at":"2021-11-24T05:44:31Z","abstract_excerpt":"Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, which becomes infeasible for high-resolution inputs. To cope with this challenge, we propose Adaptive Fourier Neural Operator (AFNO) as an efficient token mixer that learns to mix in the Fourier domain. AFNO is based on a principled foundation of operator learning which allows us to frame token mixing as a continuous global convolution without any dependence on the input resolution"},"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":"2111.13587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T05:44:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"29ceb3f06e508ace77ef01f25f59970f3e1fe75f4879e67ff696326bfcffe6ab","abstract_canon_sha256":"a1dd0a5041c33547e71213e6cee0125afeccefd9ae55408ffc9db035c92585e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:41.186722Z","signature_b64":"Tqgwx4abWSKi02I0o7oWfc/TkEEhmdfdmYRGAEt/wASa+q2WkKAOJRmigM1wUQvH+j0uT5hXvrHODD4ymM/YDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e1ebc0b1b1432cf0f5d4f7c0268cc80f69b5b1726e1c13a53a6e6b69c68ecbc","last_reissued_at":"2026-07-05T04:08:41.186276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:41.186276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Anima Anandkumar, Bryan Catanzaro, John Guibas, Morteza Mardani, Zongyi Li","submitted_at":"2021-11-24T05:44:31Z","abstract_excerpt":"Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, which becomes infeasible for high-resolution inputs. To cope with this challenge, we propose Adaptive Fourier Neural Operator (AFNO) as an efficient token mixer that learns to mix in the Fourier domain. AFNO is based on a principled foundation of operator learning which allows us to frame token mixing as a continuous global convolution without any dependence on the input resolution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13587","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.13587/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":"2111.13587","created_at":"2026-07-05T04:08:41.186333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13587v2","created_at":"2026-07-05T04:08:41.186333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13587","created_at":"2026-07-05T04:08:41.186333+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYPLYCY3CQZM","created_at":"2026-07-05T04:08:41.186333+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYPLYCY3CQZM6D25","created_at":"2026-07-05T04:08:41.186333+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYPLYCY3","created_at":"2026-07-05T04:08:41.186333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06999","citing_title":"Physics-guided spatiotemporal neural models for fuel density prediction","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26749","citing_title":"Structure Before Collapse: Transient semantic geometry in next-token prediction","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13422","citing_title":"Practical Quantum Advantage before Fault Tolerance via Quantum-Informed Machine Learning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08327","citing_title":"Chiaroscuro Attention: Spending Compute in the Dark","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07724","citing_title":"A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05618","citing_title":"Uncovering Extreme Event Mechanisms for Prediction and Control with Sensitivity-Balanced Projections","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28153","citing_title":"Skillful high-resolution weather forecasting independent of physical models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2408.00222","citing_title":"Non-markovian neural quantum propagator and its application to the simulation of ultrafast nonlinear spectra","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15793","citing_title":"AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00203","citing_title":"Estimating Parameter Fields in Multi-Physics PDEs from Scarce Measurements","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02481","citing_title":"NOWS: Neural Operator Warm Starts for Accelerating Iterative Solvers","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01486","citing_title":"Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14727","citing_title":"CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token Operators","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12965","citing_title":"U-HNO: A U-shaped Hybrid Neural Operator with Sparse-Point Adaptive Routing for Non-stationary PDE Dynamics","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26621","citing_title":"Large-eddy simulation nets (LESnets) based on physics-informed neural operator for wall-bounded turbulence","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10451","citing_title":"Don't Fix the Basis -- Learn It: Spectral Representation with Adaptive Basis Learning for PDEs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00292","citing_title":"Caracal: Causal Architecture via Spectral Mixing","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00850","citing_title":"Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17986","citing_title":"Latent Fourier Transform","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12463","citing_title":"Euler-inspired Decoupling Neural Operator for Efficient Pansharpening","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD","json":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD.json","graph_json":"https://pith.science/api/pith-number/TYPLYCY3CQZM6D25J56AE2GMQD/graph.json","events_json":"https://pith.science/api/pith-number/TYPLYCY3CQZM6D25J56AE2GMQD/events.json","paper":"https://pith.science/paper/TYPLYCY3"},"agent_actions":{"view_html":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD","download_json":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD.json","view_paper":"https://pith.science/paper/TYPLYCY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13587&json=true","fetch_graph":"https://pith.science/api/pith-number/TYPLYCY3CQZM6D25J56AE2GMQD/graph.json","fetch_events":"https://pith.science/api/pith-number/TYPLYCY3CQZM6D25J56AE2GMQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD/action/storage_attestation","attest_author":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD/action/author_attestation","sign_citation":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD/action/citation_signature","submit_replication":"https://pith.science/pith/TYPLYCY3CQZM6D25J56AE2GMQD/action/replication_record"}},"created_at":"2026-07-05T04:08:41.186333+00:00","updated_at":"2026-07-05T04:08:41.186333+00:00"}