{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z24JV6B4FTFZQCOOSFDDUREGHP","short_pith_number":"pith:Z24JV6B4","schema_version":"1.0","canonical_sha256":"ceb89af83c2ccb9809ce91463a44863bc31bea52a63757f65d7fbcefe9637e7e","source":{"kind":"arxiv","id":"2404.09101","version":3},"attestation_state":"computed","paper":{"title":"Mixtures of Neural Operators Reduce Active Complexity in Operator Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anastasis Kratsios, Jose Antonio Lara Benitez, Maarten de Hoop, Matti Lassas, Takashi Furuya","submitted_at":"2024-04-13T23:20:16Z","abstract_excerpt":"Operator-learning systems are not governed solely by total parameter count; for one query, the relevant bottleneck can be the model that must be loaded and evaluated. We study this distinction for classical neural operators on compact Sobolev subsets through a constructive comparison between routed mixtures of neural operators (MoNOs) and a fixed single-neural-operator construction. The comparison concerns expert-active complexity relative to that baseline, with total stored size and routing search accounted separately. A MoNO routes each input function through a tree to one expert. Our main t"},"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":"2404.09101","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-13T23:20:16Z","cross_cats_sorted":["cs.AI","cs.NA","math.NA","stat.ML"],"title_canon_sha256":"0f778afdfcd66021d0ab8e6437ee321a266fd01399c2212d33be217b92a0135d","abstract_canon_sha256":"8d962351d1c63f176dd0d0bfc2bddb170936da3c7c20b94b64ccc06d565301e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:08:26.161836Z","signature_b64":"EdUhSrNRiI+tx4JOH/XoT+BymEFDpgHuh86efMRMv3RSDpX0cGedYPD2ezVDfLq+ajA8ag7ESwqTDkkSx6QwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceb89af83c2ccb9809ce91463a44863bc31bea52a63757f65d7fbcefe9637e7e","last_reissued_at":"2026-06-10T01:08:26.160778Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:08:26.160778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixtures of Neural Operators Reduce Active Complexity in Operator Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anastasis Kratsios, Jose Antonio Lara Benitez, Maarten de Hoop, Matti Lassas, Takashi Furuya","submitted_at":"2024-04-13T23:20:16Z","abstract_excerpt":"Operator-learning systems are not governed solely by total parameter count; for one query, the relevant bottleneck can be the model that must be loaded and evaluated. We study this distinction for classical neural operators on compact Sobolev subsets through a constructive comparison between routed mixtures of neural operators (MoNOs) and a fixed single-neural-operator construction. The comparison concerns expert-active complexity relative to that baseline, with total stored size and routing search accounted separately. A MoNO routes each input function through a tree to one expert. Our main t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09101","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/2404.09101/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":"2404.09101","created_at":"2026-06-10T01:08:26.160921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09101v3","created_at":"2026-06-10T01:08:26.160921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09101","created_at":"2026-06-10T01:08:26.160921+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z24JV6B4FTFZ","created_at":"2026-06-10T01:08:26.160921+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z24JV6B4FTFZQCOO","created_at":"2026-06-10T01:08:26.160921+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z24JV6B4","created_at":"2026-06-10T01:08:26.160921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2501.06933","citing_title":"Neural equilibria for long-term prediction of nonlinear conservation laws","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01015","citing_title":"Upper Approximation Bounds for Neural Oscillators","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12025","citing_title":"Approximation Theory of Laplacian-Based Neural Operators for Reaction-Diffusion System","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP","json":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP.json","graph_json":"https://pith.science/api/pith-number/Z24JV6B4FTFZQCOOSFDDUREGHP/graph.json","events_json":"https://pith.science/api/pith-number/Z24JV6B4FTFZQCOOSFDDUREGHP/events.json","paper":"https://pith.science/paper/Z24JV6B4"},"agent_actions":{"view_html":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP","download_json":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP.json","view_paper":"https://pith.science/paper/Z24JV6B4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09101&json=true","fetch_graph":"https://pith.science/api/pith-number/Z24JV6B4FTFZQCOOSFDDUREGHP/graph.json","fetch_events":"https://pith.science/api/pith-number/Z24JV6B4FTFZQCOOSFDDUREGHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP/action/storage_attestation","attest_author":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP/action/author_attestation","sign_citation":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP/action/citation_signature","submit_replication":"https://pith.science/pith/Z24JV6B4FTFZQCOOSFDDUREGHP/action/replication_record"}},"created_at":"2026-06-10T01:08:26.160921+00:00","updated_at":"2026-06-10T01:08:26.160921+00:00"}