{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DENZZMRPHDFNTGOBKBYXSE34MP","short_pith_number":"pith:DENZZMRP","schema_version":"1.0","canonical_sha256":"191b9cb22f38cad999c1507179137c63f0d7c392b5e417bbb6af470863e53be2","source":{"kind":"arxiv","id":"2508.20650","version":1},"attestation_state":"computed","paper":{"title":"Self-Composing Neural Operators with Depth and Accuracy Scaling via Adaptive Train-and-Unroll Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinchao Xu, Juncai He, Xinliang Liu","submitted_at":"2025-08-28T10:53:00Z","abstract_excerpt":"In this work, we propose a novel framework to enhance the efficiency and accuracy of neural operators through self-composition, offering both theoretical guarantees and practical benefits. Inspired by iterative methods in solving numerical partial differential equations (PDEs), we design a specific neural operator by repeatedly applying a single neural operator block, we progressively deepen the model without explicitly adding new blocks, improving the model's capacity. To train these models efficiently, we introduce an adaptive train-and-unroll approach, where the depth of the neural operator"},"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":"2508.20650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T10:53:00Z","cross_cats_sorted":[],"title_canon_sha256":"acb54e13210008a4250cfc401aa90100f9525fb82b3eb4d501c87c1ea2d9fe4b","abstract_canon_sha256":"1cc98965212928241661ad04eaf0451c710a29ca5b7f6bcd1bfb872ce4266abb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:56.824389Z","signature_b64":"UJqBmBprj7uAjljepnlOcV4BQIFO65uOQfMZkgIUwBCsuD3b8MCvKAIu38qz6962G4UH3Wwi9OZNvaIHadkuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"191b9cb22f38cad999c1507179137c63f0d7c392b5e417bbb6af470863e53be2","last_reissued_at":"2026-07-05T12:00:56.823607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:56.823607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Composing Neural Operators with Depth and Accuracy Scaling via Adaptive Train-and-Unroll Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinchao Xu, Juncai He, Xinliang Liu","submitted_at":"2025-08-28T10:53:00Z","abstract_excerpt":"In this work, we propose a novel framework to enhance the efficiency and accuracy of neural operators through self-composition, offering both theoretical guarantees and practical benefits. Inspired by iterative methods in solving numerical partial differential equations (PDEs), we design a specific neural operator by repeatedly applying a single neural operator block, we progressively deepen the model without explicitly adding new blocks, improving the model's capacity. To train these models efficiently, we introduce an adaptive train-and-unroll approach, where the depth of the neural operator"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20650","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/2508.20650/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":"2508.20650","created_at":"2026-07-05T12:00:56.823726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20650v1","created_at":"2026-07-05T12:00:56.823726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20650","created_at":"2026-07-05T12:00:56.823726+00:00"},{"alias_kind":"pith_short_12","alias_value":"DENZZMRPHDFN","created_at":"2026-07-05T12:00:56.823726+00:00"},{"alias_kind":"pith_short_16","alias_value":"DENZZMRPHDFNTGOB","created_at":"2026-07-05T12:00:56.823726+00:00"},{"alias_kind":"pith_short_8","alias_value":"DENZZMRP","created_at":"2026-07-05T12:00:56.823726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.30495","citing_title":"McMg: A Learned Phase-Space Multi-channel Multigrid Preconditioner for Helmholtz Equation","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22557","citing_title":"Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30495","citing_title":"McMg: A Learned Phase-Space Multi-channel Multigrid Preconditioner for Helmholtz Equation","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22557","citing_title":"Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations","ref_index":126,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP","json":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP.json","graph_json":"https://pith.science/api/pith-number/DENZZMRPHDFNTGOBKBYXSE34MP/graph.json","events_json":"https://pith.science/api/pith-number/DENZZMRPHDFNTGOBKBYXSE34MP/events.json","paper":"https://pith.science/paper/DENZZMRP"},"agent_actions":{"view_html":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP","download_json":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP.json","view_paper":"https://pith.science/paper/DENZZMRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20650&json=true","fetch_graph":"https://pith.science/api/pith-number/DENZZMRPHDFNTGOBKBYXSE34MP/graph.json","fetch_events":"https://pith.science/api/pith-number/DENZZMRPHDFNTGOBKBYXSE34MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP/action/storage_attestation","attest_author":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP/action/author_attestation","sign_citation":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP/action/citation_signature","submit_replication":"https://pith.science/pith/DENZZMRPHDFNTGOBKBYXSE34MP/action/replication_record"}},"created_at":"2026-07-05T12:00:56.823726+00:00","updated_at":"2026-07-05T12:00:56.823726+00:00"}